关于 tokenizer 文件
#17
by
evpeople
- opened
vLLM 建议GGUF模型使用底模的tokenizer
We recommend using the tokenizer from base model to avoid long-time and buggy tokenizer conversion.
但是qwen 7b的tokenizer 中没有 做为special token，我正打算用deepseek-ai/DeepSeek-R1-Distill-Qwen-7B 试一下，但还是希望deepsex能提供tokenizer
We recommend using the tokenizer from base model instead of GGUF model. Because the tokenizer conversion from GGUF is time-consuming and unstable, especially for some models with large vocab size.
理论上 tokenizer 和原模型一样，当然还是得问问 @ValueFX9507