Open wsp317 opened 1 month ago
Oh that is an issue - the pad_token must be not the same as the eos_token, otherwise the finetune will be incorrect. I'll see if I can extend the tokenizer itself
I change the pad_token from <|endoftext|> to <|im_end|> in qwen's tokenizer_config.json file, and the training seems work.
@wsp317 I fixed it just then! Sorry on the delay! I
If you're on a local machine, please update Unsloth via
pip uninstall unsloth -y
pip install --upgrade --force-reinstall --no-cache-dir git+https://github.com/unslothai/unsloth.git
Colab and Kaggle is fine (just restart it)
训练qwen1.5-14b-chat,遇到下面的报错,transformers==4.38.2
RuntimeError( "Unsloth: Tokenizer's pad_token cannot be = eos_token, and we couldn't find a\n"\ "replacement of either <|reserved... or <|placeholder..." )