config.json

{
  "_name_or_path": "llama-30b-hf/-dequantized",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "bos_token_id": 0,
  "eos_token_id": 1,
  "hidden_act": "silu",
  "hidden_size": 6656,
  "initializer_range": 0.02,
  "intermediate_size": 17920,
  "max_position_embeddings": 4096,
  "max_sequence_length": 4096,
  "model_type": "llama",
  "num_attention_heads": 52,
  "num_hidden_layers": 60,
  "num_key_value_heads": 52,
  "pad_token_id": -1,
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
      "factor": 2.0,
      "type": "linear"
   },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.31.0",
  "use_cache": true,
  "vocab_size": 32000,
  "auto_map": {
    "AutoModel": "modelling_llama.LlamaModel",
    "AutoModelForCausalLM": "modelling_llama.LlamaForCausalLM",
    "AutoModelForSequenceClassification": "modelling_llama.LlamaForSequenceClassification"
  }
}