Skip to content

WIP [DeepSeek R1] Add DeepSeekV3 Base + Weight Conversion #2171

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 19 commits into
base: master
Choose a base branch
from
Open

WIP [DeepSeek R1] Add DeepSeekV3 Base + Weight Conversion #2171

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
e275e05
Initial commit
DavidLandup0 Mar 1, 2025
e26a0c0
full port
DavidLandup0 Mar 9, 2025
f0f5c55
Add more complete weight conversion script
DavidLandup0 Mar 27, 2025
ed0bed9
attempt to convert to functional subclassing model
DavidLandup0 Mar 27, 2025
e8fed54
Small fixes
DavidLandup0 May 2, 2025
00554bc
Finish functional subclassing model port
DavidLandup0 May 2, 2025
14882a7
use full args
DavidLandup0 May 2, 2025
5b91b17
Fix top_k usage
DavidLandup0 May 2, 2025
040e833
Move model args to config files
DavidLandup0 May 2, 2025
1c26539
Remove model args dataclasses
DavidLandup0 May 2, 2025
ffc7594
Add note and make test config match embedding dims of full config
DavidLandup0 May 31, 2025
ca96974
fix path
DavidLandup0 May 31, 2025
5c832f2
Remove unnecessary configs, add tokenizer class
DavidLandup0 Jun 22, 2025
2680a94
Add causallm class and causallmpreprocessor
DavidLandup0 Jun 22, 2025
9f117d3
Add tokenizer to conversion script
DavidLandup0 Jun 22, 2025
806b1b0
Add cpu() before numpy()
DavidLandup0 Jun 30, 2025
776d4a7
Run api_gen.sh
DavidLandup0 Jun 30, 2025
3418a12
Switch to full model parts
DavidLandup0 Jun 30, 2025
0cf6058
Remove unnecessary token copy
DavidLandup0 Jun 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
full port
  • Loading branch information
@DavidLandup0
DavidLandup0 committed Mar 9, 2025
commit e26a0c0d9b23c1342b2d9748dccaba9879e70300
Loading