pad_token errors

[tomgelu]

Trying to run chatdocs on windows, with gpu, model mistralai/Mistral-7B-Instruct-v0.1 but same error on default models..

ValueError: Pipeline with tokenizer without pad_token cannot do batching. You can try to set it with pipe.tokenizer.pad_token_id = model.config.eos_token_id.

Anyone can help ?