| { |
| "model_file": "model.safetensors", |
| "model_file_bytes": 15656878852, |
| "model_file_sha256": "4475b48270e4d2072886f084442e29f5e5eb16c7668d5a2a28404428e9c0b247", |
| "total_tensor_count": 35923, |
| "weight_packed_tensor_count": 11725, |
| "weight_scale_tensor_count": 11725, |
| "weight_scale_nonfinite_tensor_count": 0, |
| "weight_scale_nonfinite_value_count": 0, |
| "packed_exclusion_counts": { |
| "vision_tower": 0, |
| "router": 0, |
| "token_embedding": 0, |
| "vision_embedding": 0, |
| "lm_head": 0 |
| }, |
| "representative_excluded_weight_dtypes": { |
| "token_embedding": "bfloat16", |
| "vision_projection": "bfloat16", |
| "router": "bfloat16", |
| "vision_mlp": "bfloat16" |
| }, |
| "separate_lm_head_tensor_present": false, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": "pack-quantized", |
| "input_activations": null, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": "static", |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 64, |
| "num_bits": 4, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "group", |
| "symmetric": true, |
| "type": "int", |
| "zp_dtype": null |
| } |
| } |
| }, |
| "format": "pack-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "model.vision_tower.patch_embedder.input_proj", |
| "model.vision_tower.encoder.layers.0.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.0.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.0.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.0.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.0.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.0.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.0.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.1.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.1.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.1.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.2.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.2.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.2.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.3.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.3.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.3.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.3.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.3.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.3.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.3.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.4.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.4.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.4.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.4.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.4.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.4.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.4.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.5.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.5.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.5.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.6.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.6.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.6.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.7.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.7.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.7.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.7.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.7.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.7.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.7.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.8.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.8.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.8.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.8.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.8.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.8.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.8.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.9.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.9.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.9.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.9.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.9.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.9.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.9.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.10.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.10.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.10.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.10.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.10.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.10.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.10.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.11.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.11.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.11.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.12.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.12.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.12.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.13.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.13.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.13.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.14.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.14.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.14.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.15.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.15.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.15.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.16.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.16.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.16.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.17.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.17.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.17.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.17.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.17.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.17.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.17.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.18.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.18.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.18.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.18.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.18.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.18.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.18.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.19.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.19.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.19.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.20.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.20.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.20.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.20.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.20.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.20.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.20.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.21.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.21.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.21.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.22.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.22.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.22.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.23.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.23.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.23.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.24.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.24.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.24.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.24.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.24.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.24.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.24.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.25.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.25.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.25.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.26.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.26.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.26.mlp.down_proj.linear", |
| "model.language_model.layers.0.router", |
| "model.language_model.layers.0.router.proj", |
| "model.language_model.layers.1.router", |
| "model.language_model.layers.1.router.proj", |
| "model.language_model.layers.2.router", |
| "model.language_model.layers.2.router.proj", |
| "model.language_model.layers.3.router", |
| "model.language_model.layers.3.router.proj", |
| "model.language_model.layers.4.router", |
| "model.language_model.layers.4.router.proj", |
| "model.language_model.layers.5.router", |
| "model.language_model.layers.5.router.proj", |
| "model.language_model.layers.6.router", |
| "model.language_model.layers.6.router.proj", |
| "model.language_model.layers.7.router", |
| "model.language_model.layers.7.router.proj", |
| "model.language_model.layers.8.router", |
| "model.language_model.layers.8.router.proj", |
| "model.language_model.layers.9.router", |
| "model.language_model.layers.9.router.proj", |
| "model.language_model.layers.10.router", |
| "model.language_model.layers.10.router.proj", |
| "model.language_model.layers.11.router", |
| "model.language_model.layers.11.router.proj", |
| "model.language_model.layers.12.router", |
| "model.language_model.layers.12.router.proj", |
| "model.language_model.layers.13.router", |
| "model.language_model.layers.13.router.proj", |
| "model.language_model.layers.14.router", |
| "model.language_model.layers.14.router.proj", |
| "model.language_model.layers.15.router", |
| "model.language_model.layers.15.router.proj", |
| "model.language_model.layers.16.router", |
| "model.language_model.layers.16.router.proj", |
| "model.language_model.layers.17.router", |
| "model.language_model.layers.17.router.proj", |
| "model.language_model.layers.18.router", |
| "model.language_model.layers.18.router.proj", |
| "model.language_model.layers.19.router", |
| "model.language_model.layers.19.router.proj", |
| "model.language_model.layers.20.router", |
| "model.language_model.layers.20.router.proj", |
| "model.language_model.layers.21.router", |
| "model.language_model.layers.21.router.proj", |
| "model.language_model.layers.22.router", |
| "model.language_model.layers.22.router.proj", |
| "model.language_model.layers.23.router", |
| "model.language_model.layers.23.router.proj", |
| "model.language_model.layers.24.router", |
| "model.language_model.layers.24.router.proj", |
| "model.language_model.layers.25.router", |
| "model.language_model.layers.25.router.proj", |
| "model.language_model.layers.26.router", |
| "model.language_model.layers.26.router.proj", |
| "model.language_model.layers.27.router", |
| "model.language_model.layers.27.router.proj", |
| "model.language_model.layers.28.router", |
| "model.language_model.layers.28.router.proj", |
| "model.language_model.layers.29.router", |
| "model.language_model.layers.29.router.proj", |
| "model.embed_vision.embedding_projection", |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.18.0" |
| } |
| } |
|
|
