SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

fix typos (#38336)

Browse Source 
* Update video_processor.md

* Update deepseek_v3.md
This commit is contained in:
Ragnar
2025-05-26 16:42:37 +02:00
committed by GitHub
parent 8b03c8eaf2
commit 63964b7c67
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/en/model_doc/deepseek_v3.md
View File

@@ -28,8 +28,8 @@ We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 67
We are super happy to make this code community-powered, and would love to see how you can best optimize the following:
- current implementation uses the "naive" attention compution (so not really MLA)
- current implementation loops through the experts. This should be replaced. Pointers to use `get_packed_weights` from `intetrations/tensor_parallel`.
- current implementation uses the eleuther formula for ROPE, using the orginal one would be more efficient! (should still follow our API)
- current implementation loops through the experts. This should be replaced. Pointers to use `get_packed_weights` from `integrations/tensor_parallel`.
- current implementation uses the eleuther formula for ROPE, using the original one would be more efficient! (should still follow our API)
- static cache is not supported (this should be just a generation config issue / config shape issues)
### Usage tips