transformers
Deepseek v2 support
#31976
Open
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
17
Changes
View On
GitHub
Deepseek v2 support
#31976
itazap
wants to merge 17 commits into
main
from
deepseek_v2_support
adding initial version of deepseek v2 files, copied from existing rep…
43e8548f
initial ruff
e339caad
testing files
e8444402
adding tokenizer config files
48e84ed1
updating based on paper and making more meaningful naming
90554fbf
cleaning
0ee5bb74
update diff file
9d7cdbdb
update
6f66d603
removed some ep size refs
9c3a0ea8
update diff file
d8d9ac0c
update to use MoeCausalLM
afea6ca7
run script
8370023f
itazap
marked this pull request as ready for review
1 year ago
updated MOE to be like mixtral
9c524ea0
itazap
marked this pull request as draft
1 year ago
removing seperate inference logic and using mixtral for ref
c3436e4e
moe update
1feb8435
update diff file
a14b489f
add modular file
cd8b36c7
Login to write a write a comment.
Login via GitHub
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub