{
  "architectures": [
    "CohereForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 5,
  "dtype": "bfloat16",
  "eos_token_id": 255001,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "layer_norm_eps": 1e-05,
  "logit_scale": 0.125,
  "max_position_embeddings": 8192,
  "model_type": "cohere",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "pack-quantized",
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 128,
          "num_bits": 4,
          "observer": "memoryless_minmax",
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "group",
          "symmetric": false,
          "type": "int",
          "zp_dtype": "torch.int8"
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.14.0.1"
  },
  "rope_scaling": null,
  "rope_theta": 10000,
  "transformers_version": "4.57.6",
  "use_cache": true,
  "use_qk_norm": false,
  "vocab_size": 256000
}