mlc-chat-config.json

{
  "version": "0.1.0",
  "model_type": "phi3",
  "quantization": "q0f16",
  "model_config": {
    "model_type": "phi3",
    "hidden_size": 3072,
    "vocab_size": 32064,
    "num_hidden_layers": 32,
    "num_attention_heads": 32,
    "intermediate_size": 8192,
    "rms_norm_eps": 1e-05,
    "num_key_value_heads": 32,
    "max_position_embeddings": 131072,
    "position_embedding_base": 10000.0,
    "rope_scaling": {
      "long_factor": [
        1.0800000429153442,
        1.1100000143051147,
        1.1399999856948853,
        1.340000033378601,
        1.5899999141693115,
        1.600000023841858,
        1.6200000047683716,
        2.620000123977661,
        3.2300000190734863,
        3.2300000190734863,
        4.789999961853027,
        7.400000095367432,
        7.700000286102295,
        9.09000015258789,
        12.199999809265137,
        17.670000076293945,
        24.46000099182129,
        28.57000160217285,
        30.420001983642578,
        30.840002059936523,
        32.590003967285156,
        32.93000411987305,
        42.320003509521484,
        44.96000289916992,
        50.340003967285156,
        50.45000457763672,
        57.55000305175781,
        57.93000411987305,
        58.21000289916992,
        60.1400032043457,
        62.61000442504883,
        62.62000274658203,
        62.71000289916992,
        63.1400032043457,
        63.1400032043457,
        63.77000427246094,
        63.93000411987305,
        63.96000289916992,
        63.970001220703125,
        64.02999877929688,
        64.06999969482422,
        64.08000183105469,
        64.12000274658203,
        64.41000366210938,
        64.4800033569336,
        64.51000213623047,
        64.52999877929688,
        64.83999633789062
      ],
      "short_factor": [
        1.0,
        1.0199999809265137,
        1.0299999713897705,
        1.0299999713897705,
        1.0499999523162842,
        1.0499999523162842,
        1.0499999523162842,
        1.0499999523162842,
        1.0499999523162842,
        1.0699999332427979,
        1.0999999046325684,
        1.1099998950958252,
        1.1599998474121094,
        1.1599998474121094,
        1.1699998378753662,
        1.2899998426437378,
        1.339999794960022,
        1.679999828338623,
        1.7899998426437378,
        1.8199998140335083,
        1.8499997854232788,
        1.8799997568130493,
        1.9099997282028198,
        1.9399996995925903,
        1.9899996519088745,
        2.0199997425079346,
        2.0199997425079346,
        2.0199997425079346,
        2.0199997425079346,
        2.0199997425079346,
        2.0199997425079346,
        2.0299997329711914,
        2.0299997329711914,
        2.0299997329711914,
        2.0299997329711914,
        2.0299997329711914,
        2.0299997329711914,
        2.0299997329711914,
        2.0299997329711914,
        2.0299997329711914,
        2.0799996852874756,
        2.0899996757507324,
        2.189999580383301,
        2.2199995517730713,
        2.5899994373321533,
        2.729999542236328,
        2.749999523162842,
        2.8399994373321533
      ],
      "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": 2048,
    "head_dim": 96,
    "tensor_parallel_shards": 1,
    "max_batch_size": 80
  },
  "vocab_size": 32064,
  "context_window_size": 131072,
  "sliding_window_size": -1,
  "prefill_chunk_size": 2048,
  "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.model",
    "tokenizer.json",
    "added_tokens.json",
    "tokenizer_config.json"
  ],
  "tokenizer_info": {
    "token_postproc_method": "byte_fallback",
    "prepend_space_in_encode": true,
    "strip_space_in_decode": true
  },
  "conv_template": {
    "name": "phi-3",
    "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": [
      1
    ],
    "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|>"
    ],
    "stop_token_ids": [
      32000,
      32001,
      32007
    ],
    "function_string": "",
    "use_function_calling": false
  },
  "pad_token_id": 32000,
  "bos_token_id": 1,
  "eos_token_id": [
    32007,
    32001,
    32000
  ]
}