可亲
fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm
688e28d
| { | |
| "chat_format": "chatml", | |
| "do_sample": true, | |
| "eos_token_id": 151643, | |
| "max_new_tokens": 512, | |
| "max_window_size": 6144, | |
| "pad_token_id": 151643, | |
| "top_k": 0, | |
| "top_p": 0.01, | |
| "transformers_version": "4.45.0.dev0" | |
| } | |