mlc-chat-config.json

{
  "model_type": "gpt_bigcode",
  "quantization": "q4f32_1",
  "model_config": {
    "n_embd": 2048,
    "n_inner": 8192,
    "n_head": 16,
    "n_layer": 24,
    "n_positions": 2048,
    "layer_norm_epsilon": 1e-05,
    "vocab_size": 49280,
    "context_window_size": 2048,
    "prefill_chunk_size": 2048,
    "tensor_parallel_shards": 1
  },
  "vocab_size": 49280,
  "context_window_size": 2048,
  "sliding_window_size": -1,
  "prefill_chunk_size": 2048,
  "attention_sink_size": -1,
  "tensor_parallel_shards": 1,
  "max_batch_size": 80,
  "mean_gen_len": 128,
  "max_gen_len": 512,
  "shift_fill_factor": 0.3,
  "temperature": 0.7,
  "repetition_penalty": 1.0,
  "top_p": 0.95,
  "conv_template": "LM",
  "pad_token_id": 0,
  "bos_token_id": 49152,
  "eos_token_id": 49152,
  "tokenizer_files": [
    "tokenizer.json",
    "tokenizer_config.json"
  ],
  "version": "0.1.0"
}