Error loading llama3 tokenizer

ictnlp / LLaMA-Omni

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

https://arxiv.org/abs/2409.06666

Apache License 2.0

2.63k stars 177 forks source link

Error loading llama3 tokenizer #2

Closed hexastrayer closed 2 months ago

hexastrayer commented 2 months ago

Incorrect path_or_model_id: '/data/fangqingkai/Omni/models/LLM/Meta-Llama-3-8B-Instruct'. Please provide either the path to a local folder or the repo_id of a model on the Hub.

Poeroz commented 2 months ago

Thank you for pointing out the error. We accidentally included an absolute path in the code, but it's not needed. You can safely delete it, and we've already fixed this issue in the new version.