mlc-chat-config.json

{
  "version": "0.1.0",
  "model_type": "phi3",
  "quantization": "q4f16_1",
  "model_config": {
    "model_type": "phi3",
    "hidden_size": 3072,
    "vocab_size": 200064,
    "num_hidden_layers": 32,
    "num_attention_heads": 24,
    "intermediate_size": 8192,
    "rms_norm_eps": 1e-05,
    "num_key_value_heads": 8,
    "max_position_embeddings": 131072,
    "position_embedding_base": 10000.0,
    "rope_scaling": {
      "long_factor": [
        1,
        1.118320672,
        1.250641126,
        1.398617824,
        1.564103225,
        1.74916897,
        1.956131817,
        2.187582649,
        2.446418898,
        2.735880826,
        3.059592084,
        3.421605075,
        3.826451687,
        4.279200023,
        4.785517845,
        5.351743533,
        5.984965424,
        6.693110555,
        7.485043894,
        8.370679318,
        9.36110372,
        10.4687158,
        11.70738129,
        13.09260651,
        14.64173252,
        16.37415215,
        18.31155283,
        20.47818807,
        22.90118105,
        25.61086418,
        28.64115884,
        32.03,
        32.1,
        32.13,
        32.23,
        32.6,
        32.61,
        32.64,
        32.66,
        32.7,
        32.71,
        32.93,
        32.97,
        33.28,
        33.49,
        33.5,
        44.16,
        47.77
      ],
      "short_factor": [
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "type": "longrope",
      "rope_type": "longrope",
      "max_position_embeddings": 131072,
      "original_max_position_embeddings": 4096
    },
    "original_max_position_embeddings": 4096,
    "context_window_size": 131072,
    "prefill_chunk_size": 8192,
    "head_dim": 128,
    "tensor_parallel_shards": 1,
    "max_batch_size": 128,
    "tie_word_embeddings": true,
    "partial_rotary_factor": 0.75
  },
  "vocab_size": 200064,
  "context_window_size": 131072,
  "sliding_window_size": -1,
  "prefill_chunk_size": 8192,
  "attention_sink_size": -1,
  "tensor_parallel_shards": 1,
  "pipeline_parallel_stages": 1,
  "temperature": 1.0,
  "presence_penalty": 0.0,
  "frequency_penalty": 0.0,
  "repetition_penalty": 1.0,
  "top_p": 1.0,
  "tokenizer_files": [
    "tokenizer.json",
    "vocab.json",
    "merges.txt",
    "added_tokens.json",
    "tokenizer_config.json"
  ],
  "tokenizer_info": {
    "token_postproc_method": "byte_level",
    "prepend_space_in_encode": false,
    "strip_space_in_decode": false
  },
  "conv_template": {
    "name": "phi-4",
    "system_template": "<|system|>\n{system_message}",
    "system_message": "You are a helpful digital assistant. Please provide safe, ethical and accurate information to the user.",
    "system_prefix_token_ids": [
      200022
    ],
    "add_role_after_system_message": true,
    "roles": {
      "user": "<|user|>",
      "assistant": "<|assistant|>"
    },
    "role_templates": {
      "user": "{user_message}",
      "assistant": "{assistant_message}",
      "tool": "{tool_message}"
    },
    "messages": [],
    "seps": [
      "<|end|>\n"
    ],
    "role_content_sep": "\n",
    "role_empty_sep": "\n",
    "stop_str": [
      "<|endoftext|>",
      "<|end|>"
    ],
    "stop_token_ids": [
      199999,
      200020
    ],
    "function_string": "",
    "use_function_calling": false
  },
  "pad_token_id": 199999,
  "bos_token_id": 199999,
  "eos_token_id": [
    200020,
    199999
  ]
}