You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This is rather low priority. I found it confusing chasing down the occurrences of cache_kwargs to try to understand how sin and cos are getting used in the Cache, presumably for RoPE, but it appears they are only used in the SinkCache which, as far as I can tell, isn't commonly made use of by any transformer. cache_positions appears to be used, but not sin and cos.
This dead bit of code shows up in 3 popular models, but also many others, and I don't think it has any bearing on anything at all:
System Info
This is rather low priority. I found it confusing chasing down the occurrences of
cache_kwargs
to try to understand howsin
andcos
are getting used in theCache
, presumably for RoPE, but it appears they are only used in theSinkCache
which, as far as I can tell, isn't commonly made use of by any transformer.cache_positions
appears to be used, but notsin
andcos
.This dead bit of code shows up in 3 popular models, but also many others, and I don't think it has any bearing on anything at all:
Llama: https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/modeling_llama.py#L339
Mistral: https://github.com/huggingface/transformers/blob/main/src/transformers/models/mistral/modeling_mistral.py#L255
Qwen: https://github.com/huggingface/transformers/blob/main/src/transformers/models/qwen2/modeling_qwen2.py#L278
Per your tagging request: @ArthurZucker, and I saw @zucchini-nlp and @zhenglongjiepheonix in git-blame
And sorry if this is just noise, I'll shut up about small stuff if you like.
Who can help?
No response
Information
Tasks
examples
folder (such as GLUE/SQuAD, ...)Reproduction
nothing to reproduce, just dead code
Expected behavior
just dead code
The text was updated successfully, but these errors were encountered: