huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-19 11:56:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Implement DeepSeek V2 (#2744)

Browse Source 
* Add deepseek v2

* Fix

* Remove unused

* Add kv cache

* Remove from cargo.toml

* Fix dtype selection logic

* Fix unnecessary u32->f32->gather->u32

* Remove fromstr impl

* Use local scopes for some clarity

* Typo

* Repeat k_pe

* Chain calls to remove mut

* Actually, remove all muts

* Update readme
This commit is contained in:
Eric Buehler
2025-02-19 04:51:01 -05:00
committed by GitHub
parent fd7f7242a1
commit e6cc76fc37
4 changed files with 1367 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1051
candle-transformers/src/models/deepseek2.rs Normal file
View File

File diff suppressed because it is too large Load Diff

1
candle-transformers/src/models/mod.rs
View File

@ -29,6 +29,7 @@ pub mod convmixer;
pub mod convnext;
pub mod dac;
pub mod debertav2;
pub mod deepseek2;
pub mod depth_anything_v2;
pub mod dinov2;
pub mod dinov2reg4;