c4ai-command-a-03-2025-exl3-4.25bpw / quantization_config.json
DBMe's picture
Upload folder using huggingface_hub
67c351b verified
Raw
History Blame Contribute Delete
453 kB
{
"quant_method": "exl3",
"version": "0.0.6",
"bits": 4.25,
"head_bits": 6,
"calibration": {
"rows": 100,
"cols": 2048
},
"out_scales": "auto",
"tensor_storage": {
"model.embed_tokens": {
"stored_tensors": {
"model.embed_tokens.weight": {
"shape": [
256000,
12288
],
"n_bytes": 6291456000,
"dtype": "torch.float16"
}
}
},
"model.layers.0.input_layernorm": {
"stored_tensors": {
"model.layers.0.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.0.self_attn.q_proj": {
"stored_tensors": {
"model.layers.0.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.0.self_attn.k_proj": {
"stored_tensors": {
"model.layers.0.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.0.self_attn.v_proj": {
"stored_tensors": {
"model.layers.0.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.0.self_attn.o_proj": {
"stored_tensors": {
"model.layers.0.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.0.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.0.mlp.up_proj": {
"stored_tensors": {
"model.layers.0.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.0.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.0.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.0.mlp.gate_proj": {
"stored_tensors": {
"model.layers.0.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.0.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.0.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.0.mlp.down_proj": {
"stored_tensors": {
"model.layers.0.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.0.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.0.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.1.input_layernorm": {
"stored_tensors": {
"model.layers.1.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.1.self_attn.q_proj": {
"stored_tensors": {
"model.layers.1.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.1.self_attn.k_proj": {
"stored_tensors": {
"model.layers.1.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.1.self_attn.v_proj": {
"stored_tensors": {
"model.layers.1.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.1.self_attn.o_proj": {
"stored_tensors": {
"model.layers.1.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.1.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.1.mlp.up_proj": {
"stored_tensors": {
"model.layers.1.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.1.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.1.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.1.mlp.gate_proj": {
"stored_tensors": {
"model.layers.1.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.1.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.1.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.1.mlp.down_proj": {
"stored_tensors": {
"model.layers.1.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.1.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.1.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.2.input_layernorm": {
"stored_tensors": {
"model.layers.2.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.2.self_attn.q_proj": {
"stored_tensors": {
"model.layers.2.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.2.self_attn.k_proj": {
"stored_tensors": {
"model.layers.2.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.2.self_attn.v_proj": {
"stored_tensors": {
"model.layers.2.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.2.self_attn.o_proj": {
"stored_tensors": {
"model.layers.2.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.2.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.2.mlp.up_proj": {
"stored_tensors": {
"model.layers.2.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.2.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.2.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.2.mlp.gate_proj": {
"stored_tensors": {
"model.layers.2.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.2.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.2.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.2.mlp.down_proj": {
"stored_tensors": {
"model.layers.2.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.2.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.2.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.3.input_layernorm": {
"stored_tensors": {
"model.layers.3.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.3.self_attn.q_proj": {
"stored_tensors": {
"model.layers.3.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.3.self_attn.k_proj": {
"stored_tensors": {
"model.layers.3.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.3.self_attn.v_proj": {
"stored_tensors": {
"model.layers.3.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.3.self_attn.o_proj": {
"stored_tensors": {
"model.layers.3.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.3.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.3.mlp.up_proj": {
"stored_tensors": {
"model.layers.3.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.3.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.3.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.3.mlp.gate_proj": {
"stored_tensors": {
"model.layers.3.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.3.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.3.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.3.mlp.down_proj": {
"stored_tensors": {
"model.layers.3.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.3.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.3.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.4.input_layernorm": {
"stored_tensors": {
"model.layers.4.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.4.self_attn.q_proj": {
"stored_tensors": {
"model.layers.4.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.4.self_attn.k_proj": {
"stored_tensors": {
"model.layers.4.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.4.self_attn.v_proj": {
"stored_tensors": {
"model.layers.4.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.4.self_attn.o_proj": {
"stored_tensors": {
"model.layers.4.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.4.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.4.mlp.up_proj": {
"stored_tensors": {
"model.layers.4.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.4.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.4.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.4.mlp.gate_proj": {
"stored_tensors": {
"model.layers.4.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.4.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.4.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.4.mlp.down_proj": {
"stored_tensors": {
"model.layers.4.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.4.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.4.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.5.input_layernorm": {
"stored_tensors": {
"model.layers.5.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.5.self_attn.q_proj": {
"stored_tensors": {
"model.layers.5.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.5.self_attn.k_proj": {
"stored_tensors": {
"model.layers.5.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.5.self_attn.v_proj": {
"stored_tensors": {
"model.layers.5.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.5.self_attn.o_proj": {
"stored_tensors": {
"model.layers.5.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.5.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.5.mlp.up_proj": {
"stored_tensors": {
"model.layers.5.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.5.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.5.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.5.mlp.gate_proj": {
"stored_tensors": {
"model.layers.5.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.5.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.5.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.5.mlp.down_proj": {
"stored_tensors": {
"model.layers.5.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.5.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.5.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.6.input_layernorm": {
"stored_tensors": {
"model.layers.6.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.6.self_attn.q_proj": {
"stored_tensors": {
"model.layers.6.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.6.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.6.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.6.self_attn.k_proj": {
"stored_tensors": {
"model.layers.6.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.6.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.6.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.6.self_attn.v_proj": {
"stored_tensors": {
"model.layers.6.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.6.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.6.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.6.self_attn.o_proj": {
"stored_tensors": {
"model.layers.6.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.6.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.6.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.6.mlp.up_proj": {
"stored_tensors": {
"model.layers.6.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.6.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.6.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.6.mlp.gate_proj": {
"stored_tensors": {
"model.layers.6.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.6.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.6.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.6.mlp.down_proj": {
"stored_tensors": {
"model.layers.6.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.6.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.6.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.7.input_layernorm": {
"stored_tensors": {
"model.layers.7.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.7.self_attn.q_proj": {
"stored_tensors": {
"model.layers.7.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.7.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.7.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.7.self_attn.k_proj": {
"stored_tensors": {
"model.layers.7.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.7.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.7.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.7.self_attn.v_proj": {
"stored_tensors": {
"model.layers.7.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.7.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.7.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.7.self_attn.o_proj": {
"stored_tensors": {
"model.layers.7.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.7.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.7.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.7.mlp.up_proj": {
"stored_tensors": {
"model.layers.7.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.7.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.7.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.7.mlp.gate_proj": {
"stored_tensors": {
"model.layers.7.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.7.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.7.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.7.mlp.down_proj": {
"stored_tensors": {
"model.layers.7.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.7.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.7.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.8.input_layernorm": {
"stored_tensors": {
"model.layers.8.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.8.self_attn.q_proj": {
"stored_tensors": {
"model.layers.8.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.8.self_attn.k_proj": {
"stored_tensors": {
"model.layers.8.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.8.self_attn.v_proj": {
"stored_tensors": {
"model.layers.8.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.8.self_attn.o_proj": {
"stored_tensors": {
"model.layers.8.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.8.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.8.mlp.up_proj": {
"stored_tensors": {
"model.layers.8.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.8.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.8.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.8.mlp.gate_proj": {
"stored_tensors": {
"model.layers.8.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.8.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.8.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.8.mlp.down_proj": {
"stored_tensors": {
"model.layers.8.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.8.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.8.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.9.input_layernorm": {
"stored_tensors": {
"model.layers.9.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.9.self_attn.q_proj": {
"stored_tensors": {
"model.layers.9.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.9.self_attn.k_proj": {
"stored_tensors": {
"model.layers.9.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.9.self_attn.v_proj": {
"stored_tensors": {
"model.layers.9.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.9.self_attn.o_proj": {
"stored_tensors": {
"model.layers.9.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.9.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.9.mlp.up_proj": {
"stored_tensors": {
"model.layers.9.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.9.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.9.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.9.mlp.gate_proj": {
"stored_tensors": {
"model.layers.9.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.9.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.9.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.9.mlp.down_proj": {
"stored_tensors": {
"model.layers.9.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.9.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.9.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.10.input_layernorm": {
"stored_tensors": {
"model.layers.10.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.10.self_attn.q_proj": {
"stored_tensors": {
"model.layers.10.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.10.self_attn.k_proj": {
"stored_tensors": {
"model.layers.10.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.10.self_attn.v_proj": {
"stored_tensors": {
"model.layers.10.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.10.self_attn.o_proj": {
"stored_tensors": {
"model.layers.10.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.10.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.10.mlp.up_proj": {
"stored_tensors": {
"model.layers.10.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.10.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.10.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.10.mlp.gate_proj": {
"stored_tensors": {
"model.layers.10.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.10.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.10.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.10.mlp.down_proj": {
"stored_tensors": {
"model.layers.10.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.10.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.10.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.11.input_layernorm": {
"stored_tensors": {
"model.layers.11.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.11.self_attn.q_proj": {
"stored_tensors": {
"model.layers.11.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.11.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.11.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.11.self_attn.k_proj": {
"stored_tensors": {
"model.layers.11.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.11.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.11.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.11.self_attn.v_proj": {
"stored_tensors": {
"model.layers.11.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.11.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.11.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.11.self_attn.o_proj": {
"stored_tensors": {
"model.layers.11.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.11.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.11.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.11.mlp.up_proj": {
"stored_tensors": {
"model.layers.11.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.11.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.11.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.11.mlp.gate_proj": {
"stored_tensors": {
"model.layers.11.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.11.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.11.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.11.mlp.down_proj": {
"stored_tensors": {
"model.layers.11.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.11.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.11.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.12.input_layernorm": {
"stored_tensors": {
"model.layers.12.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.12.self_attn.q_proj": {
"stored_tensors": {
"model.layers.12.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.12.self_attn.k_proj": {
"stored_tensors": {
"model.layers.12.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.12.self_attn.v_proj": {
"stored_tensors": {
"model.layers.12.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.12.self_attn.o_proj": {
"stored_tensors": {
"model.layers.12.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.12.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.12.mlp.up_proj": {
"stored_tensors": {
"model.layers.12.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.12.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.12.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.12.mlp.gate_proj": {
"stored_tensors": {
"model.layers.12.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.12.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.12.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.12.mlp.down_proj": {
"stored_tensors": {
"model.layers.12.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.12.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.12.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.13.input_layernorm": {
"stored_tensors": {
"model.layers.13.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.13.self_attn.q_proj": {
"stored_tensors": {
"model.layers.13.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.13.self_attn.k_proj": {
"stored_tensors": {
"model.layers.13.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.13.self_attn.v_proj": {
"stored_tensors": {
"model.layers.13.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.13.self_attn.o_proj": {
"stored_tensors": {
"model.layers.13.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.13.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.13.mlp.up_proj": {
"stored_tensors": {
"model.layers.13.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.13.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.13.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.13.mlp.gate_proj": {
"stored_tensors": {
"model.layers.13.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.13.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.13.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.13.mlp.down_proj": {
"stored_tensors": {
"model.layers.13.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.13.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.13.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.14.input_layernorm": {
"stored_tensors": {
"model.layers.14.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.14.self_attn.q_proj": {
"stored_tensors": {
"model.layers.14.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.14.self_attn.k_proj": {
"stored_tensors": {
"model.layers.14.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.14.self_attn.v_proj": {
"stored_tensors": {
"model.layers.14.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.14.self_attn.o_proj": {
"stored_tensors": {
"model.layers.14.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.14.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.14.mlp.up_proj": {
"stored_tensors": {
"model.layers.14.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.14.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.14.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.14.mlp.gate_proj": {
"stored_tensors": {
"model.layers.14.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.14.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.14.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.14.mlp.down_proj": {
"stored_tensors": {
"model.layers.14.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.14.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.14.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.15.input_layernorm": {
"stored_tensors": {
"model.layers.15.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.15.self_attn.q_proj": {
"stored_tensors": {
"model.layers.15.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.15.self_attn.k_proj": {
"stored_tensors": {
"model.layers.15.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.15.self_attn.v_proj": {
"stored_tensors": {
"model.layers.15.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.15.self_attn.o_proj": {
"stored_tensors": {
"model.layers.15.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.15.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.15.mlp.up_proj": {
"stored_tensors": {
"model.layers.15.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.15.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.15.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.15.mlp.gate_proj": {
"stored_tensors": {
"model.layers.15.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.15.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.15.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.15.mlp.down_proj": {
"stored_tensors": {
"model.layers.15.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.15.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.15.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.16.input_layernorm": {
"stored_tensors": {
"model.layers.16.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.16.self_attn.q_proj": {
"stored_tensors": {
"model.layers.16.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.16.self_attn.k_proj": {
"stored_tensors": {
"model.layers.16.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.16.self_attn.v_proj": {
"stored_tensors": {
"model.layers.16.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.16.self_attn.o_proj": {
"stored_tensors": {
"model.layers.16.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.16.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.16.mlp.up_proj": {
"stored_tensors": {
"model.layers.16.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.16.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.16.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.16.mlp.gate_proj": {
"stored_tensors": {
"model.layers.16.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.16.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.16.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.16.mlp.down_proj": {
"stored_tensors": {
"model.layers.16.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.16.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.16.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.17.input_layernorm": {
"stored_tensors": {
"model.layers.17.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.17.self_attn.q_proj": {
"stored_tensors": {
"model.layers.17.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.17.self_attn.k_proj": {
"stored_tensors": {
"model.layers.17.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.17.self_attn.v_proj": {
"stored_tensors": {
"model.layers.17.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.17.self_attn.o_proj": {
"stored_tensors": {
"model.layers.17.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.17.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.17.mlp.up_proj": {
"stored_tensors": {
"model.layers.17.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.17.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.17.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.17.mlp.gate_proj": {
"stored_tensors": {
"model.layers.17.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.17.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.17.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.17.mlp.down_proj": {
"stored_tensors": {
"model.layers.17.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.17.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.17.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.18.input_layernorm": {
"stored_tensors": {
"model.layers.18.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.18.self_attn.q_proj": {
"stored_tensors": {
"model.layers.18.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.18.self_attn.k_proj": {
"stored_tensors": {
"model.layers.18.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.18.self_attn.v_proj": {
"stored_tensors": {
"model.layers.18.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.18.self_attn.o_proj": {
"stored_tensors": {
"model.layers.18.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.18.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.18.mlp.up_proj": {
"stored_tensors": {
"model.layers.18.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.18.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.18.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.18.mlp.gate_proj": {
"stored_tensors": {
"model.layers.18.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.18.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.18.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.18.mlp.down_proj": {
"stored_tensors": {
"model.layers.18.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.18.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.18.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.19.input_layernorm": {
"stored_tensors": {
"model.layers.19.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.19.self_attn.q_proj": {
"stored_tensors": {
"model.layers.19.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.19.self_attn.k_proj": {
"stored_tensors": {
"model.layers.19.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.19.self_attn.v_proj": {
"stored_tensors": {
"model.layers.19.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.19.self_attn.o_proj": {
"stored_tensors": {
"model.layers.19.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.19.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.19.mlp.up_proj": {
"stored_tensors": {
"model.layers.19.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.19.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.19.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.19.mlp.gate_proj": {
"stored_tensors": {
"model.layers.19.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.19.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.19.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.19.mlp.down_proj": {
"stored_tensors": {
"model.layers.19.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.19.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.19.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.20.input_layernorm": {
"stored_tensors": {
"model.layers.20.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.20.self_attn.q_proj": {
"stored_tensors": {
"model.layers.20.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.20.self_attn.k_proj": {
"stored_tensors": {
"model.layers.20.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.20.self_attn.v_proj": {
"stored_tensors": {
"model.layers.20.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.20.self_attn.o_proj": {
"stored_tensors": {
"model.layers.20.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.20.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.20.mlp.up_proj": {
"stored_tensors": {
"model.layers.20.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.20.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.20.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.20.mlp.gate_proj": {
"stored_tensors": {
"model.layers.20.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.20.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.20.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.20.mlp.down_proj": {
"stored_tensors": {
"model.layers.20.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.20.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.20.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.21.input_layernorm": {
"stored_tensors": {
"model.layers.21.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.21.self_attn.q_proj": {
"stored_tensors": {
"model.layers.21.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.21.self_attn.k_proj": {
"stored_tensors": {
"model.layers.21.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.21.self_attn.v_proj": {
"stored_tensors": {
"model.layers.21.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.21.self_attn.o_proj": {
"stored_tensors": {
"model.layers.21.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.21.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.21.mlp.up_proj": {
"stored_tensors": {
"model.layers.21.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.21.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.21.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.21.mlp.gate_proj": {
"stored_tensors": {
"model.layers.21.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.21.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.21.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.21.mlp.down_proj": {
"stored_tensors": {
"model.layers.21.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.21.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.21.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.22.input_layernorm": {
"stored_tensors": {
"model.layers.22.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.22.self_attn.q_proj": {
"stored_tensors": {
"model.layers.22.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.22.self_attn.k_proj": {
"stored_tensors": {
"model.layers.22.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.22.self_attn.v_proj": {
"stored_tensors": {
"model.layers.22.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.22.self_attn.o_proj": {
"stored_tensors": {
"model.layers.22.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.22.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.22.mlp.up_proj": {
"stored_tensors": {
"model.layers.22.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.22.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.22.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.22.mlp.gate_proj": {
"stored_tensors": {
"model.layers.22.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.22.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.22.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.22.mlp.down_proj": {
"stored_tensors": {
"model.layers.22.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.22.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.22.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.23.input_layernorm": {
"stored_tensors": {
"model.layers.23.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.23.self_attn.q_proj": {
"stored_tensors": {
"model.layers.23.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.23.self_attn.k_proj": {
"stored_tensors": {
"model.layers.23.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.23.self_attn.v_proj": {
"stored_tensors": {
"model.layers.23.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.23.self_attn.o_proj": {
"stored_tensors": {
"model.layers.23.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.23.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.23.mlp.up_proj": {
"stored_tensors": {
"model.layers.23.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.23.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.23.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.23.mlp.gate_proj": {
"stored_tensors": {
"model.layers.23.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.23.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.23.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.23.mlp.down_proj": {
"stored_tensors": {
"model.layers.23.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.23.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.23.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.24.input_layernorm": {
"stored_tensors": {
"model.layers.24.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.24.self_attn.q_proj": {
"stored_tensors": {
"model.layers.24.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.24.self_attn.k_proj": {
"stored_tensors": {
"model.layers.24.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.24.self_attn.v_proj": {
"stored_tensors": {
"model.layers.24.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.24.self_attn.o_proj": {
"stored_tensors": {
"model.layers.24.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.24.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.24.mlp.up_proj": {
"stored_tensors": {
"model.layers.24.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.24.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.24.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.24.mlp.gate_proj": {
"stored_tensors": {
"model.layers.24.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.24.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.24.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.24.mlp.down_proj": {
"stored_tensors": {
"model.layers.24.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.24.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.24.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.25.input_layernorm": {
"stored_tensors": {
"model.layers.25.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.25.self_attn.q_proj": {
"stored_tensors": {
"model.layers.25.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.25.self_attn.k_proj": {
"stored_tensors": {
"model.layers.25.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.25.self_attn.v_proj": {
"stored_tensors": {
"model.layers.25.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.25.self_attn.o_proj": {
"stored_tensors": {
"model.layers.25.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.25.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.25.mlp.up_proj": {
"stored_tensors": {
"model.layers.25.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.25.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.25.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.25.mlp.gate_proj": {
"stored_tensors": {
"model.layers.25.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.25.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.25.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.25.mlp.down_proj": {
"stored_tensors": {
"model.layers.25.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.25.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.25.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.26.input_layernorm": {
"stored_tensors": {
"model.layers.26.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.26.self_attn.q_proj": {
"stored_tensors": {
"model.layers.26.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.26.self_attn.k_proj": {
"stored_tensors": {
"model.layers.26.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.26.self_attn.v_proj": {
"stored_tensors": {
"model.layers.26.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.26.self_attn.o_proj": {
"stored_tensors": {
"model.layers.26.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.26.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.26.mlp.up_proj": {
"stored_tensors": {
"model.layers.26.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.26.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.26.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.26.mlp.gate_proj": {
"stored_tensors": {
"model.layers.26.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.26.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.26.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.26.mlp.down_proj": {
"stored_tensors": {
"model.layers.26.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.26.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.26.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.27.input_layernorm": {
"stored_tensors": {
"model.layers.27.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.27.self_attn.q_proj": {
"stored_tensors": {
"model.layers.27.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.27.self_attn.k_proj": {
"stored_tensors": {
"model.layers.27.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.27.self_attn.v_proj": {
"stored_tensors": {
"model.layers.27.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.27.self_attn.o_proj": {
"stored_tensors": {
"model.layers.27.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.27.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.27.mlp.up_proj": {
"stored_tensors": {
"model.layers.27.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.27.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.27.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.27.mlp.gate_proj": {
"stored_tensors": {
"model.layers.27.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.27.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.27.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.27.mlp.down_proj": {
"stored_tensors": {
"model.layers.27.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.27.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.27.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.28.input_layernorm": {
"stored_tensors": {
"model.layers.28.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.28.self_attn.q_proj": {
"stored_tensors": {
"model.layers.28.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.28.self_attn.k_proj": {
"stored_tensors": {
"model.layers.28.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.28.self_attn.v_proj": {
"stored_tensors": {
"model.layers.28.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.28.self_attn.o_proj": {
"stored_tensors": {
"model.layers.28.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.28.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.28.mlp.up_proj": {
"stored_tensors": {
"model.layers.28.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.28.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.28.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.28.mlp.gate_proj": {
"stored_tensors": {
"model.layers.28.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.28.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.28.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.28.mlp.down_proj": {
"stored_tensors": {
"model.layers.28.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.28.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.28.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.29.input_layernorm": {
"stored_tensors": {
"model.layers.29.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.29.self_attn.q_proj": {
"stored_tensors": {
"model.layers.29.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.29.self_attn.k_proj": {
"stored_tensors": {
"model.layers.29.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.29.self_attn.v_proj": {
"stored_tensors": {
"model.layers.29.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.29.self_attn.o_proj": {
"stored_tensors": {
"model.layers.29.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.29.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.29.mlp.up_proj": {
"stored_tensors": {
"model.layers.29.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.29.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.29.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.29.mlp.gate_proj": {
"stored_tensors": {
"model.layers.29.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.29.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.29.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.29.mlp.down_proj": {
"stored_tensors": {
"model.layers.29.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.29.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.29.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.30.input_layernorm": {
"stored_tensors": {
"model.layers.30.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.30.self_attn.q_proj": {
"stored_tensors": {
"model.layers.30.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.30.self_attn.k_proj": {
"stored_tensors": {
"model.layers.30.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.30.self_attn.v_proj": {
"stored_tensors": {
"model.layers.30.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.30.self_attn.o_proj": {
"stored_tensors": {
"model.layers.30.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.30.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.30.mlp.up_proj": {
"stored_tensors": {
"model.layers.30.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.30.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.30.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.30.mlp.gate_proj": {
"stored_tensors": {
"model.layers.30.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.30.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.30.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.30.mlp.down_proj": {
"stored_tensors": {
"model.layers.30.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.30.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.30.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.31.input_layernorm": {
"stored_tensors": {
"model.layers.31.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.31.self_attn.q_proj": {
"stored_tensors": {
"model.layers.31.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.31.self_attn.k_proj": {
"stored_tensors": {
"model.layers.31.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.31.self_attn.v_proj": {
"stored_tensors": {
"model.layers.31.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.31.self_attn.o_proj": {
"stored_tensors": {
"model.layers.31.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.31.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.31.mlp.up_proj": {
"stored_tensors": {
"model.layers.31.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.31.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.31.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.31.mlp.gate_proj": {
"stored_tensors": {
"model.layers.31.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.31.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.31.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.31.mlp.down_proj": {
"stored_tensors": {
"model.layers.31.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.31.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.31.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.32.input_layernorm": {
"stored_tensors": {
"model.layers.32.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.32.self_attn.q_proj": {
"stored_tensors": {
"model.layers.32.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.32.self_attn.k_proj": {
"stored_tensors": {
"model.layers.32.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.32.self_attn.v_proj": {
"stored_tensors": {
"model.layers.32.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.32.self_attn.o_proj": {
"stored_tensors": {
"model.layers.32.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.32.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.32.mlp.up_proj": {
"stored_tensors": {
"model.layers.32.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.32.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.32.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.32.mlp.gate_proj": {
"stored_tensors": {
"model.layers.32.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.32.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.32.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.32.mlp.down_proj": {
"stored_tensors": {
"model.layers.32.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.32.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.32.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.33.input_layernorm": {
"stored_tensors": {
"model.layers.33.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.33.self_attn.q_proj": {
"stored_tensors": {
"model.layers.33.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.33.self_attn.k_proj": {
"stored_tensors": {
"model.layers.33.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.33.self_attn.v_proj": {
"stored_tensors": {
"model.layers.33.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.33.self_attn.o_proj": {
"stored_tensors": {
"model.layers.33.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.33.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.33.mlp.up_proj": {
"stored_tensors": {
"model.layers.33.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.33.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.33.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.33.mlp.gate_proj": {
"stored_tensors": {
"model.layers.33.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.33.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.33.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.33.mlp.down_proj": {
"stored_tensors": {
"model.layers.33.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.33.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.33.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.34.input_layernorm": {
"stored_tensors": {
"model.layers.34.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.34.self_attn.q_proj": {
"stored_tensors": {
"model.layers.34.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.34.self_attn.k_proj": {
"stored_tensors": {
"model.layers.34.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.34.self_attn.v_proj": {
"stored_tensors": {
"model.layers.34.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.34.self_attn.o_proj": {
"stored_tensors": {
"model.layers.34.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.34.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.34.mlp.up_proj": {
"stored_tensors": {
"model.layers.34.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.34.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.34.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.34.mlp.gate_proj": {
"stored_tensors": {
"model.layers.34.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.34.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.34.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.34.mlp.down_proj": {
"stored_tensors": {
"model.layers.34.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.34.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.34.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.35.input_layernorm": {
"stored_tensors": {
"model.layers.35.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.35.self_attn.q_proj": {
"stored_tensors": {
"model.layers.35.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.35.self_attn.k_proj": {
"stored_tensors": {
"model.layers.35.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.35.self_attn.v_proj": {
"stored_tensors": {
"model.layers.35.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.35.self_attn.o_proj": {
"stored_tensors": {
"model.layers.35.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.35.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.35.mlp.up_proj": {
"stored_tensors": {
"model.layers.35.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.35.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.35.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.35.mlp.gate_proj": {
"stored_tensors": {
"model.layers.35.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.35.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.35.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.35.mlp.down_proj": {
"stored_tensors": {
"model.layers.35.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.35.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.35.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.36.input_layernorm": {
"stored_tensors": {
"model.layers.36.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.36.self_attn.q_proj": {
"stored_tensors": {
"model.layers.36.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.36.self_attn.k_proj": {
"stored_tensors": {
"model.layers.36.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.36.self_attn.v_proj": {
"stored_tensors": {
"model.layers.36.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.36.self_attn.o_proj": {
"stored_tensors": {
"model.layers.36.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.36.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.36.mlp.up_proj": {
"stored_tensors": {
"model.layers.36.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.36.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.36.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.36.mlp.gate_proj": {
"stored_tensors": {
"model.layers.36.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.36.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.36.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.36.mlp.down_proj": {
"stored_tensors": {
"model.layers.36.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.36.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.36.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.37.input_layernorm": {
"stored_tensors": {
"model.layers.37.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.37.self_attn.q_proj": {
"stored_tensors": {
"model.layers.37.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.37.self_attn.k_proj": {
"stored_tensors": {
"model.layers.37.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.37.self_attn.v_proj": {
"stored_tensors": {
"model.layers.37.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.37.self_attn.o_proj": {
"stored_tensors": {
"model.layers.37.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.37.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.37.mlp.up_proj": {
"stored_tensors": {
"model.layers.37.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.37.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.37.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.37.mlp.gate_proj": {
"stored_tensors": {
"model.layers.37.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.37.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.37.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.37.mlp.down_proj": {
"stored_tensors": {
"model.layers.37.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.37.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.37.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.38.input_layernorm": {
"stored_tensors": {
"model.layers.38.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.38.self_attn.q_proj": {
"stored_tensors": {
"model.layers.38.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.38.self_attn.k_proj": {
"stored_tensors": {
"model.layers.38.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.38.self_attn.v_proj": {
"stored_tensors": {
"model.layers.38.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.38.self_attn.o_proj": {
"stored_tensors": {
"model.layers.38.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.38.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.38.mlp.up_proj": {
"stored_tensors": {
"model.layers.38.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.38.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.38.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.38.mlp.gate_proj": {
"stored_tensors": {
"model.layers.38.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.38.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.38.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.38.mlp.down_proj": {
"stored_tensors": {
"model.layers.38.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.38.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.38.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.39.input_layernorm": {
"stored_tensors": {
"model.layers.39.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.39.self_attn.q_proj": {
"stored_tensors": {
"model.layers.39.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.39.self_attn.k_proj": {
"stored_tensors": {
"model.layers.39.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.39.self_attn.v_proj": {
"stored_tensors": {
"model.layers.39.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.39.self_attn.o_proj": {
"stored_tensors": {
"model.layers.39.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.39.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.39.mlp.up_proj": {
"stored_tensors": {
"model.layers.39.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.39.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.39.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.39.mlp.gate_proj": {
"stored_tensors": {
"model.layers.39.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.39.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.39.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.39.mlp.down_proj": {
"stored_tensors": {
"model.layers.39.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.39.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.39.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.40.input_layernorm": {
"stored_tensors": {
"model.layers.40.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.40.self_attn.q_proj": {
"stored_tensors": {
"model.layers.40.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.40.self_attn.k_proj": {
"stored_tensors": {
"model.layers.40.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.40.self_attn.v_proj": {
"stored_tensors": {
"model.layers.40.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.40.self_attn.o_proj": {
"stored_tensors": {
"model.layers.40.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.40.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.40.mlp.up_proj": {
"stored_tensors": {
"model.layers.40.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.40.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.40.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.40.mlp.gate_proj": {
"stored_tensors": {
"model.layers.40.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.40.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.40.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.40.mlp.down_proj": {
"stored_tensors": {
"model.layers.40.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.40.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.40.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.41.input_layernorm": {
"stored_tensors": {
"model.layers.41.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.41.self_attn.q_proj": {
"stored_tensors": {
"model.layers.41.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.41.self_attn.k_proj": {
"stored_tensors": {
"model.layers.41.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.41.self_attn.v_proj": {
"stored_tensors": {
"model.layers.41.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.41.self_attn.o_proj": {
"stored_tensors": {
"model.layers.41.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.41.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.41.mlp.up_proj": {
"stored_tensors": {
"model.layers.41.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.41.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.41.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.41.mlp.gate_proj": {
"stored_tensors": {
"model.layers.41.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.41.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.41.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.41.mlp.down_proj": {
"stored_tensors": {
"model.layers.41.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.41.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.41.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.42.input_layernorm": {
"stored_tensors": {
"model.layers.42.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.42.self_attn.q_proj": {
"stored_tensors": {
"model.layers.42.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.42.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.42.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.42.self_attn.k_proj": {
"stored_tensors": {
"model.layers.42.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.42.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.42.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.42.self_attn.v_proj": {
"stored_tensors": {
"model.layers.42.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.42.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.42.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.42.self_attn.o_proj": {
"stored_tensors": {
"model.layers.42.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.42.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.42.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.42.mlp.up_proj": {
"stored_tensors": {
"model.layers.42.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.42.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.42.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.42.mlp.gate_proj": {
"stored_tensors": {
"model.layers.42.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.42.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.42.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.42.mlp.down_proj": {
"stored_tensors": {
"model.layers.42.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.42.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.42.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.43.input_layernorm": {
"stored_tensors": {
"model.layers.43.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.43.self_attn.q_proj": {
"stored_tensors": {
"model.layers.43.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.43.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.43.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.43.self_attn.k_proj": {
"stored_tensors": {
"model.layers.43.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.43.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.43.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.43.self_attn.v_proj": {
"stored_tensors": {
"model.layers.43.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.43.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.43.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.43.self_attn.o_proj": {
"stored_tensors": {
"model.layers.43.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.43.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.43.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.43.mlp.up_proj": {
"stored_tensors": {
"model.layers.43.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.43.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.43.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.43.mlp.gate_proj": {
"stored_tensors": {
"model.layers.43.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.43.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.43.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.43.mlp.down_proj": {
"stored_tensors": {
"model.layers.43.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.43.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.43.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.44.input_layernorm": {
"stored_tensors": {
"model.layers.44.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.44.self_attn.q_proj": {
"stored_tensors": {
"model.layers.44.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.44.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.44.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.44.self_attn.k_proj": {
"stored_tensors": {
"model.layers.44.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.44.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.44.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.44.self_attn.v_proj": {
"stored_tensors": {
"model.layers.44.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.44.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.44.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.44.self_attn.o_proj": {
"stored_tensors": {
"model.layers.44.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.44.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.44.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.44.mlp.up_proj": {
"stored_tensors": {
"model.layers.44.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.44.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.44.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.44.mlp.gate_proj": {
"stored_tensors": {
"model.layers.44.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.44.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.44.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.44.mlp.down_proj": {
"stored_tensors": {
"model.layers.44.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.44.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.44.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.45.input_layernorm": {
"stored_tensors": {
"model.layers.45.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.45.self_attn.q_proj": {
"stored_tensors": {
"model.layers.45.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.45.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.45.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.45.self_attn.k_proj": {
"stored_tensors": {
"model.layers.45.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.45.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.45.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.45.self_attn.v_proj": {
"stored_tensors": {
"model.layers.45.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.45.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.45.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.45.self_attn.o_proj": {
"stored_tensors": {
"model.layers.45.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.45.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.45.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.45.mlp.up_proj": {
"stored_tensors": {
"model.layers.45.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.45.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.45.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.45.mlp.gate_proj": {
"stored_tensors": {
"model.layers.45.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.45.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.45.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.45.mlp.down_proj": {
"stored_tensors": {
"model.layers.45.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.45.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.45.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.46.input_layernorm": {
"stored_tensors": {
"model.layers.46.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.46.self_attn.q_proj": {
"stored_tensors": {
"model.layers.46.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.46.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.46.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.46.self_attn.k_proj": {
"stored_tensors": {
"model.layers.46.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.46.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.46.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.46.self_attn.v_proj": {
"stored_tensors": {
"model.layers.46.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.46.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.46.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.46.self_attn.o_proj": {
"stored_tensors": {
"model.layers.46.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.46.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.46.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.46.mlp.up_proj": {
"stored_tensors": {
"model.layers.46.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.46.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.46.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.46.mlp.gate_proj": {
"stored_tensors": {
"model.layers.46.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.46.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.46.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.46.mlp.down_proj": {
"stored_tensors": {
"model.layers.46.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.46.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.46.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.47.input_layernorm": {
"stored_tensors": {
"model.layers.47.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.47.self_attn.q_proj": {
"stored_tensors": {
"model.layers.47.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.47.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.47.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.47.self_attn.k_proj": {
"stored_tensors": {
"model.layers.47.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.47.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.47.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.47.self_attn.v_proj": {
"stored_tensors": {
"model.layers.47.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.47.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.47.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.47.self_attn.o_proj": {
"stored_tensors": {
"model.layers.47.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.47.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.47.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.47.mlp.up_proj": {
"stored_tensors": {
"model.layers.47.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.47.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.47.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.47.mlp.gate_proj": {
"stored_tensors": {
"model.layers.47.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.47.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.47.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.47.mlp.down_proj": {
"stored_tensors": {
"model.layers.47.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.47.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.47.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.48.input_layernorm": {
"stored_tensors": {
"model.layers.48.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.48.self_attn.q_proj": {
"stored_tensors": {
"model.layers.48.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.48.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.48.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.48.self_attn.k_proj": {
"stored_tensors": {
"model.layers.48.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.48.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.48.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.48.self_attn.v_proj": {
"stored_tensors": {
"model.layers.48.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.48.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.48.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.48.self_attn.o_proj": {
"stored_tensors": {
"model.layers.48.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.48.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.48.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.48.mlp.up_proj": {
"stored_tensors": {
"model.layers.48.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.48.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.48.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.48.mlp.gate_proj": {
"stored_tensors": {
"model.layers.48.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.48.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.48.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.48.mlp.down_proj": {
"stored_tensors": {
"model.layers.48.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.48.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.48.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.49.input_layernorm": {
"stored_tensors": {
"model.layers.49.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.49.self_attn.q_proj": {
"stored_tensors": {
"model.layers.49.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.49.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.49.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.49.self_attn.k_proj": {
"stored_tensors": {
"model.layers.49.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.49.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.49.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.49.self_attn.v_proj": {
"stored_tensors": {
"model.layers.49.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.49.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.49.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.49.self_attn.o_proj": {
"stored_tensors": {
"model.layers.49.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.49.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.49.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.49.mlp.up_proj": {
"stored_tensors": {
"model.layers.49.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.49.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.49.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.49.mlp.gate_proj": {
"stored_tensors": {
"model.layers.49.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.49.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.49.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.49.mlp.down_proj": {
"stored_tensors": {
"model.layers.49.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.49.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.49.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.50.input_layernorm": {
"stored_tensors": {
"model.layers.50.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.50.self_attn.q_proj": {
"stored_tensors": {
"model.layers.50.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.50.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.50.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.50.self_attn.k_proj": {
"stored_tensors": {
"model.layers.50.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.50.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.50.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.50.self_attn.v_proj": {
"stored_tensors": {
"model.layers.50.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.50.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.50.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.50.self_attn.o_proj": {
"stored_tensors": {
"model.layers.50.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.50.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.50.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.50.mlp.up_proj": {
"stored_tensors": {
"model.layers.50.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.50.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.50.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.50.mlp.gate_proj": {
"stored_tensors": {
"model.layers.50.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.50.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.50.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.50.mlp.down_proj": {
"stored_tensors": {
"model.layers.50.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.50.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.50.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.51.input_layernorm": {
"stored_tensors": {
"model.layers.51.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.51.self_attn.q_proj": {
"stored_tensors": {
"model.layers.51.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.51.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.51.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.51.self_attn.k_proj": {
"stored_tensors": {
"model.layers.51.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.51.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.51.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.51.self_attn.v_proj": {
"stored_tensors": {
"model.layers.51.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.51.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.51.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.51.self_attn.o_proj": {
"stored_tensors": {
"model.layers.51.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.51.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.51.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.51.mlp.up_proj": {
"stored_tensors": {
"model.layers.51.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.51.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.51.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.51.mlp.gate_proj": {
"stored_tensors": {
"model.layers.51.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.51.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.51.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.51.mlp.down_proj": {
"stored_tensors": {
"model.layers.51.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.51.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.51.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.52.input_layernorm": {
"stored_tensors": {
"model.layers.52.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.52.self_attn.q_proj": {
"stored_tensors": {
"model.layers.52.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.52.self_attn.k_proj": {
"stored_tensors": {
"model.layers.52.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.52.self_attn.v_proj": {
"stored_tensors": {
"model.layers.52.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.52.self_attn.o_proj": {
"stored_tensors": {
"model.layers.52.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.52.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.52.mlp.up_proj": {
"stored_tensors": {
"model.layers.52.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.52.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.52.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.52.mlp.gate_proj": {
"stored_tensors": {
"model.layers.52.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.52.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.52.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.52.mlp.down_proj": {
"stored_tensors": {
"model.layers.52.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.52.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.52.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.53.input_layernorm": {
"stored_tensors": {
"model.layers.53.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.53.self_attn.q_proj": {
"stored_tensors": {
"model.layers.53.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.53.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.53.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.53.self_attn.k_proj": {
"stored_tensors": {
"model.layers.53.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.53.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.53.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.53.self_attn.v_proj": {
"stored_tensors": {
"model.layers.53.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.53.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.53.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.53.self_attn.o_proj": {
"stored_tensors": {
"model.layers.53.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.53.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.53.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.53.mlp.up_proj": {
"stored_tensors": {
"model.layers.53.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.53.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.53.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.53.mlp.gate_proj": {
"stored_tensors": {
"model.layers.53.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.53.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.53.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.53.mlp.down_proj": {
"stored_tensors": {
"model.layers.53.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.53.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.53.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.54.input_layernorm": {
"stored_tensors": {
"model.layers.54.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.54.self_attn.q_proj": {
"stored_tensors": {
"model.layers.54.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.54.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.54.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.54.self_attn.k_proj": {
"stored_tensors": {
"model.layers.54.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.54.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.54.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.54.self_attn.v_proj": {
"stored_tensors": {
"model.layers.54.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.54.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.54.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.54.self_attn.o_proj": {
"stored_tensors": {
"model.layers.54.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.54.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.54.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.54.mlp.up_proj": {
"stored_tensors": {
"model.layers.54.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.54.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.54.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.54.mlp.gate_proj": {
"stored_tensors": {
"model.layers.54.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.54.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.54.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.54.mlp.down_proj": {
"stored_tensors": {
"model.layers.54.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.54.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.54.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.55.input_layernorm": {
"stored_tensors": {
"model.layers.55.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.55.self_attn.q_proj": {
"stored_tensors": {
"model.layers.55.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.55.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.55.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.55.self_attn.k_proj": {
"stored_tensors": {
"model.layers.55.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.55.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.55.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.55.self_attn.v_proj": {
"stored_tensors": {
"model.layers.55.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.55.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.55.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.55.self_attn.o_proj": {
"stored_tensors": {
"model.layers.55.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.55.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.55.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.55.mlp.up_proj": {
"stored_tensors": {
"model.layers.55.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.55.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.55.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.55.mlp.gate_proj": {
"stored_tensors": {
"model.layers.55.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.55.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.55.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.55.mlp.down_proj": {
"stored_tensors": {
"model.layers.55.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.55.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.55.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.56.input_layernorm": {
"stored_tensors": {
"model.layers.56.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.56.self_attn.q_proj": {
"stored_tensors": {
"model.layers.56.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.56.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.56.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.56.self_attn.k_proj": {
"stored_tensors": {
"model.layers.56.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.56.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.56.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.56.self_attn.v_proj": {
"stored_tensors": {
"model.layers.56.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.56.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.56.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.56.self_attn.o_proj": {
"stored_tensors": {
"model.layers.56.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.56.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.56.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.56.mlp.up_proj": {
"stored_tensors": {
"model.layers.56.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.56.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.56.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.56.mlp.gate_proj": {
"stored_tensors": {
"model.layers.56.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.56.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.56.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.56.mlp.down_proj": {
"stored_tensors": {
"model.layers.56.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.56.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.56.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.57.input_layernorm": {
"stored_tensors": {
"model.layers.57.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.57.self_attn.q_proj": {
"stored_tensors": {
"model.layers.57.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.57.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.57.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.57.self_attn.k_proj": {
"stored_tensors": {
"model.layers.57.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.57.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.57.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.57.self_attn.v_proj": {
"stored_tensors": {
"model.layers.57.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.57.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.57.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.57.self_attn.o_proj": {
"stored_tensors": {
"model.layers.57.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.57.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.57.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.57.mlp.up_proj": {
"stored_tensors": {
"model.layers.57.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.57.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.57.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.57.mlp.gate_proj": {
"stored_tensors": {
"model.layers.57.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.57.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.57.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.57.mlp.down_proj": {
"stored_tensors": {
"model.layers.57.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.57.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.57.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.58.input_layernorm": {
"stored_tensors": {
"model.layers.58.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.58.self_attn.q_proj": {
"stored_tensors": {
"model.layers.58.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.58.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.58.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.58.self_attn.k_proj": {
"stored_tensors": {
"model.layers.58.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.58.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.58.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.58.self_attn.v_proj": {
"stored_tensors": {
"model.layers.58.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.58.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.58.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.58.self_attn.o_proj": {
"stored_tensors": {
"model.layers.58.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.58.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.58.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.58.mlp.up_proj": {
"stored_tensors": {
"model.layers.58.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.58.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.58.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.58.mlp.gate_proj": {
"stored_tensors": {
"model.layers.58.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.58.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.58.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.58.mlp.down_proj": {
"stored_tensors": {
"model.layers.58.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.58.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.58.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.59.input_layernorm": {
"stored_tensors": {
"model.layers.59.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.59.self_attn.q_proj": {
"stored_tensors": {
"model.layers.59.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.59.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.59.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.59.self_attn.k_proj": {
"stored_tensors": {
"model.layers.59.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.59.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.59.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.59.self_attn.v_proj": {
"stored_tensors": {
"model.layers.59.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.59.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.59.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.59.self_attn.o_proj": {
"stored_tensors": {
"model.layers.59.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.59.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.59.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.59.mlp.up_proj": {
"stored_tensors": {
"model.layers.59.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.59.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.59.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.59.mlp.gate_proj": {
"stored_tensors": {
"model.layers.59.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.59.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.59.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.59.mlp.down_proj": {
"stored_tensors": {
"model.layers.59.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.59.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.59.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.60.input_layernorm": {
"stored_tensors": {
"model.layers.60.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.60.self_attn.q_proj": {
"stored_tensors": {
"model.layers.60.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.60.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.60.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.60.self_attn.k_proj": {
"stored_tensors": {
"model.layers.60.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.60.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.60.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.60.self_attn.v_proj": {
"stored_tensors": {
"model.layers.60.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.60.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.60.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.60.self_attn.o_proj": {
"stored_tensors": {
"model.layers.60.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.60.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.60.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.60.mlp.up_proj": {
"stored_tensors": {
"model.layers.60.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.60.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.60.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.60.mlp.gate_proj": {
"stored_tensors": {
"model.layers.60.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.60.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.60.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.60.mlp.down_proj": {
"stored_tensors": {
"model.layers.60.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.60.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.60.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.61.input_layernorm": {
"stored_tensors": {
"model.layers.61.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.61.self_attn.q_proj": {
"stored_tensors": {
"model.layers.61.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.61.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.61.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.61.self_attn.k_proj": {
"stored_tensors": {
"model.layers.61.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.61.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.61.self_attn.k_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.61.self_attn.v_proj": {
"stored_tensors": {
"model.layers.61.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.61.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.61.self_attn.v_proj.trellis": {
"shape": [
768,
64,
80
],
"n_bytes": 7864320,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.61.self_attn.o_proj": {
"stored_tensors": {
"model.layers.61.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.61.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.61.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.61.mlp.up_proj": {
"stored_tensors": {
"model.layers.61.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.61.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.61.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.61.mlp.gate_proj": {
"stored_tensors": {
"model.layers.61.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.61.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.61.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.61.mlp.down_proj": {
"stored_tensors": {
"model.layers.61.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.61.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.61.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.62.input_layernorm": {
"stored_tensors": {
"model.layers.62.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.62.self_attn.q_proj": {
"stored_tensors": {
"model.layers.62.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.62.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.62.self_attn.q_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.62.self_attn.k_proj": {
"stored_tensors": {
"model.layers.62.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.62.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.62.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.62.self_attn.v_proj": {
"stored_tensors": {
"model.layers.62.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.62.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.62.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.62.self_attn.o_proj": {
"stored_tensors": {
"model.layers.62.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.62.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.62.self_attn.o_proj.trellis": {
"shape": [
768,
768,
80
],
"n_bytes": 94371840,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.layers.62.mlp.up_proj": {
"stored_tensors": {
"model.layers.62.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.62.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.62.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.62.mlp.gate_proj": {
"stored_tensors": {
"model.layers.62.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.62.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.62.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.62.mlp.down_proj": {
"stored_tensors": {
"model.layers.62.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.62.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.62.mlp.down_proj.trellis": {
"shape": [
2304,
768,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.63.input_layernorm": {
"stored_tensors": {
"model.layers.63.input_layernorm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"model.layers.63.self_attn.q_proj": {
"stored_tensors": {
"model.layers.63.self_attn.q_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.63.self_attn.q_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.63.self_attn.q_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.63.self_attn.k_proj": {
"stored_tensors": {
"model.layers.63.self_attn.k_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.63.self_attn.k_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.63.self_attn.k_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.63.self_attn.v_proj": {
"stored_tensors": {
"model.layers.63.self_attn.v_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.63.self_attn.v_proj.svh": {
"shape": [
1024
],
"n_bytes": 2048,
"dtype": "torch.float16"
},
"model.layers.63.self_attn.v_proj.trellis": {
"shape": [
768,
64,
96
],
"n_bytes": 9437184,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
},
"model.layers.63.self_attn.o_proj": {
"stored_tensors": {
"model.layers.63.self_attn.o_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.63.self_attn.o_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.63.self_attn.o_proj.trellis": {
"shape": [
768,
768,
64
],
"n_bytes": 75497472,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.63.mlp.up_proj": {
"stored_tensors": {
"model.layers.63.mlp.up_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.63.mlp.up_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.63.mlp.up_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.63.mlp.gate_proj": {
"stored_tensors": {
"model.layers.63.mlp.gate_proj.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.63.mlp.gate_proj.svh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.63.mlp.gate_proj.trellis": {
"shape": [
768,
2304,
64
],
"n_bytes": 226492416,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 4
},
"model.layers.63.mlp.down_proj": {
"stored_tensors": {
"model.layers.63.mlp.down_proj.suh": {
"shape": [
36864
],
"n_bytes": 73728,
"dtype": "torch.float16"
},
"model.layers.63.mlp.down_proj.svh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"model.layers.63.mlp.down_proj.trellis": {
"shape": [
2304,
768,
80
],
"n_bytes": 283115520,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 5
},
"model.norm": {
"stored_tensors": {
"model.norm.weight": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
}
}
},
"lm_head": {
"stored_tensors": {
"lm_head.suh": {
"shape": [
12288
],
"n_bytes": 24576,
"dtype": "torch.float16"
},
"lm_head.svh": {
"shape": [
256000
],
"n_bytes": 512000,
"dtype": "torch.float16"
},
"lm_head.trellis": {
"shape": [
768,
16000,
96
],
"n_bytes": 2359296000,
"dtype": "torch.int16"
}
},
"quant_format": "exl3",
"bits_per_weight": 6
}
}
}