.ipynb_checkpoints/config-checkpoint.json

{
  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "quantization_config": {
    "codebook": "E8P12RVQ4B",
    "codesz": 8,
    "idx_dtype": "torch.int32",
    "merge_suv": false,
    "modules_to_not_convert": null,
    "opt_resid_scale": -1,
    "per_channel": false,
    "quant_method": "QUiP",
    "rescale_WH": false,
    "use_rand": true
  },
  "rms_norm_eps": 1e-05,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.44.0",
  "use_cache": true,
  "vocab_size": 32000,
  "quantization" : {
      "quant_method": "QUiP",
      "rescale_WH": false,
      "use_rand": true,
      "codebook": "E8P12RVQ4B",
      "codesz": 8,
      "idx_dtype": "torch.int32",
      "merge_suv": false,
      "per_channel": false,
      "opt_resid_scale": -1,
      "modules_to_not_convert": null
  }
}