mlc-chat-config.json

{
  "version": "0.1.0",
  "model_type": "llama",
  "quantization": "q4f32_1",
  "model_config": {
    "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "bos_token_id": 1,
    "eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "max_position_embeddings": 4096,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 32,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.32.0.dev0",
    "use_cache": true,
    "vocab_size": 32000
  },
  "vocab_size": 32000,
  "max_window_size": 4096,
  "temperature": 0.6,
  "repetition_penalty": 1.0,
  "top_p": 0.9,
  "mean_gen_len": 128,
  "max_gen_len": 512,
  "shift_fill_factor": 0.3,
  "conv_template": "llama-2",
  "pad_token_id": 0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "tokenizer_files": [
    "tokenizer.model",
    "tokenizer.json",
    "tokenizer_config.json"
  ]
}