RuntimeError: Internal: could not parse ModelProto from ./vicuna/tokenizer.model

Vision-CAIR / MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

https://minigpt-4.github.io

BSD 3-Clause "New" or "Revised" License

25.42k stars 2.92k forks source link

RuntimeError: Internal: could not parse ModelProto from ./vicuna/tokenizer.model #496

Open bzr1 opened 8 months ago

bzr1 commented 8 months ago

got this error when trying to use 13B model, followed every step, don't now why

ShenZhen0502 commented 7 months ago

if using llama,you should use Llama-2-7b-chat-hf model that is suitable for transformers library of huggingface. Note, dont use llama-2-7b-chat. the usage of vicuna should be similar to it .