LocalLLaMA

1 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 10 months ago

MODERATORS

communick@poweruser.forum

Qwen-72B released (huggingface.co)

submitted 9 months ago by PookaMacPhellimen@alien.top to c/localllama@poweruser.forum

39 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] extopico@alien.top 1 points 9 months ago (1 children)

I wonder what the performance degradation is after quantising. For other models some users reported that quantizing greatly affected other language capabilities and this model seems to be at leash 50% Chinese.

permalink
fedilink
source
hideshow 2 child comments

[–] Art10001@alien.top 1 points 9 months ago

I've seen that ChatGLM began talking in mixed Chinese/English when asked "What tips do you have for a mountaineering trip?"

permalink
fedilink
source
parent