config.json

{
  "_name_or_path": "/slot/sandbox/j/_tmp/datali3qvr41",
  "architectures": [
    "CohereForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 5,
  "eos_token_id": 255001,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 22528,
  "layer_norm_eps": 1e-05,
  "logit_scale": 0.0625,
  "max_position_embeddings": 8192,
  "model_max_length": 131072,
  "model_type": "cohere",
  "num_attention_heads": 64,
  "num_hidden_layers": 40,
  "num_key_value_heads": 64,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "quantization_config": {
    "in_group_size": 8,
    "linear_weights_not_to_quantize": [
      "model.layers.0.input_layernorm.weight",
      "model.layers.1.input_layernorm.weight",
      "model.layers.2.input_layernorm.weight",
      "model.layers.3.input_layernorm.weight",
      "model.layers.4.input_layernorm.weight",
      "model.layers.5.input_layernorm.weight",
      "model.layers.6.input_layernorm.weight",
      "model.layers.7.input_layernorm.weight",
      "model.layers.8.input_layernorm.weight",
      "model.layers.9.input_layernorm.weight",
      "model.layers.10.input_layernorm.weight",
      "model.layers.11.input_layernorm.weight",
      "model.layers.12.input_layernorm.weight",
      "model.layers.13.input_layernorm.weight",
      "model.layers.14.input_layernorm.weight",
      "model.layers.15.input_layernorm.weight",
      "model.layers.16.input_layernorm.weight",
      "model.layers.17.input_layernorm.weight",
      "model.layers.18.input_layernorm.weight",
      "model.layers.19.input_layernorm.weight",
      "model.layers.20.input_layernorm.weight",
      "model.layers.21.input_layernorm.weight",
      "model.layers.22.input_layernorm.weight",
      "model.layers.23.input_layernorm.weight",
      "model.layers.24.input_layernorm.weight",
      "model.layers.25.input_layernorm.weight",
      "model.layers.26.input_layernorm.weight",
      "model.layers.27.input_layernorm.weight",
      "model.layers.28.input_layernorm.weight",
      "model.layers.29.input_layernorm.weight",
      "model.layers.30.input_layernorm.weight",
      "model.layers.31.input_layernorm.weight",
      "model.layers.32.input_layernorm.weight",
      "model.layers.33.input_layernorm.weight",
      "model.layers.34.input_layernorm.weight",
      "model.layers.35.input_layernorm.weight",
      "model.layers.36.input_layernorm.weight",
      "model.layers.37.input_layernorm.weight",
      "model.layers.38.input_layernorm.weight",
      "model.layers.39.input_layernorm.weight",
      "model.embed_tokens.weight",
      "model.norm.weight",
      "lm_head.weight"
    ],
    "nbits_per_codebook": 16,
    "num_codebooks": 1,
    "out_group_size": 1,
    "quant_method": "aqlm"
  },
  "rope_theta": 8000000.0,
  "torch_dtype": "float16",
  "transformers_version": "4.40.0.dev0",
  "use_cache": true,
  "vocab_size": 256000
}