{
  "model_type": "gpt2",
  "quantization": "q0f16",
  "model_config": {
    "vocab_size": 50257,
    "n_embd": 1024,
    "n_layer": 24,
    "n_head": 16,
    "layer_norm_epsilon": 1e-05,
    "n_inner": 4096,
    "context_window_size": 1024,
    "prefill_chunk_size": 1024,
    "scale_attn_by_inverse_layer_idx": false,
    "tensor_parallel_shards": 1,
    "max_batch_size": 80
  },
  "vocab_size": 50257,
  "context_window_size": 1024,
  "sliding_window_size": -1,
  "prefill_chunk_size": 1024,
  "attention_sink_size": -1,
  "tensor_parallel_shards": 1,
  "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": {
    "name": "gpt2",
    "system_template": "{system_message}",
    "system_message": "",
    "add_role_after_system_message": true,
    "roles": {
      "user": "",
      "assistant": ""
    },
    "role_templates": {
      "user": "{user_message}",
      "assistant": "{assistant_message}",
      "tool": "{tool_message}"
    },
    "messages": [],
    "seps": [
      ""
    ],
    "role_content_sep": "",
    "role_empty_sep": "",
    "stop_str": [
      "</s>"
    ],
    "stop_token_ids": [
      50256
    ],
    "function_string": "",
    "use_function_calling": false
  },
  "pad_token_id": 0,
  "bos_token_id": 50256,
  "eos_token_id": 50256,
  "tokenizer_files": [
    "tokenizer.json",
    "vocab.json",
    "merges.txt"
  ],
  "version": "0.1.0"
}