| { | |
| "model_type": "qwen", | |
| "quantization": "q4f32_1", | |
| "model_config": { | |
| "vocab_size": 152064, | |
| "hidden_size": 5120, | |
| "num_hidden_layers": 40, | |
| "num_attention_heads": 40, | |
| "layer_norm_epsilon": 1e-06, | |
| "scale_attn_weights": true, | |
| "kv_channels": 128, | |
| "rotary_emb_base": 10000, | |
| "intermediate_size": 27392, | |
| "context_window_size": 8192, | |
| "prefill_chunk_size": 8192, | |
| "tensor_parallel_shards": 1, | |
| "max_batch_size": 80 | |
| }, | |
| "vocab_size": 152064, | |
| "context_window_size": 8192, | |
| "sliding_window_size": -1, | |
| "prefill_chunk_size": 8192, | |
| "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": 1.1, | |
| "top_p": 0.8, | |
| "conv_template": { | |
| "name": "chatml", | |
| "system_template": "<|im_start|>system\n{system_message}", | |
| "system_message": "A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.", | |
| "add_role_after_system_message": true, | |
| "roles": { | |
| "user": "<|im_start|>user", | |
| "assistant": "<|im_start|>assistant" | |
| }, | |
| "role_templates": { | |
| "user": "{user_message}", | |
| "assistant": "{assistant_message}", | |
| "tool": "{tool_message}" | |
| }, | |
| "messages": [], | |
| "seps": [ | |
| "<|im_end|>\n" | |
| ], | |
| "role_content_sep": "\n", | |
| "role_empty_sep": "\n", | |
| "stop_str": [ | |
| "<|im_end|>" | |
| ], | |
| "stop_token_ids": [ | |
| 151643 | |
| ], | |
| "function_string": "", | |
| "use_function_calling": false | |
| }, | |
| "pad_token_id": 151643, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "tokenizer_files": [ | |
| "tokenizer_config.json" | |
| ], | |
| "version": "0.1.0" | |
| } |