Wrong EOS token has been fixed in upstream tokenizer_config.json, consider reconverting
#2
by
compilade - opened
llama.cpp's ./main example uses the EOS token stored in the GGUF to figure out when to stop.
For context, convert-hf-to-gguf.py uses transformers.AutoTokenizer which uses settings from tokenizer_config.json.
The EOS token was wrong (but was recently fixed upstream), so the output never seemed to end when I first tried this model.
Consider re-converting this model so that the GGUF files contain the correct EOS token (which should be <|im_end|> (aka token id 50279) for this model).
compilade changed discussion status to
closed