mlc-chat-config.json

{
  "model_type": "qwen2",
  "quantization": "q4f16_1",
  "model_config": {
    "hidden_act": "silu",
    "hidden_size": 2048,
    "intermediate_size": 5504,
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "num_key_value_heads": 16,
    "rms_norm_eps": 1e-06,
    "rope_theta": 1000000.0,
    "vocab_size": 151936,
    "context_window_size": 768,
    "prefill_chunk_size": 768,
    "tensor_parallel_shards": 1,
    "head_dim": 128,
    "dtype": "float32"
  },
  "vocab_size": 151936,
  "context_window_size": 768,
  "sliding_window_size": -1,
  "prefill_chunk_size": 768,
  "attention_sink_size": -1,
  "tensor_parallel_shards": 1,
  "mean_gen_len": 128,
  "max_gen_len": 512,
  "shift_fill_factor": 0.3,
  "temperature": 0.7,
  "presence_penalty": 0.0,
  "frequency_penalty": 0.0,
  "repetition_penalty": 1.1,
  "top_p": 0.8,
  "conv_template": {
    "name": "llama-2",
    "system_template": "[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n",
    "system_message": "You are a helpful, respectful and honest assistant.",
    "system_prefix_token_ids": [
      1
    ],
    "add_role_after_system_message": false,
    "roles": {
      "user": "<s>[INST]",
      "assistant": "[/INST]",
      "tool": "[INST]"
    },
    "role_templates": {
      "user": "{user_message}",
      "assistant": "{assistant_message}",
      "tool": "{tool_message}"
    },
    "messages": [],
    "seps": [
      " ",
      " </s>"
    ],
    "role_content_sep": " ",
    "role_empty_sep": " ",
    "stop_str": [
      "[INST]"
    ],
    "stop_token_ids": [
      2
    ],
    "function_string": "",
    "use_function_calling": false
  },
  "pad_token_id": 151643,
  "bos_token_id": 151643,
  "eos_token_id": [
    151645,
    151643
  ],
  "tokenizer_files": [
    "tokenizer.json",
    "vocab.json",
    "merges.txt",
    "tokenizer_config.json"
  ],
  "token_table_postproc_method": "byte_level",
  "version": "0.1.0"
}