Skip to content
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.

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

[Finetune] Integrate DPO trainer for CPU and Gaudi #238

Open
wants to merge 58 commits into
base: main
Choose a base branch
from

Conversation

minmingzhu
Copy link
Contributor

No description provided.

llm_on_ray/common/dataprocesser/dpo_processer.py Outdated Show resolved Hide resolved
llm_on_ray/finetune/finetune.py Show resolved Hide resolved
llm_on_ray/common/dataprocesser/dpo_processer.py Outdated Show resolved Hide resolved
llm_on_ray/common/dataprocesser/dpo_processer.py Outdated Show resolved Hide resolved
llm_on_ray/common/dataset/huggingface_dataset.py Outdated Show resolved Hide resolved
@minmingzhu minmingzhu force-pushed the integrate_dpo branch 2 times, most recently from 2550635 to 3f66e59 Compare June 5, 2024 06:58
llm_on_ray/finetune/finetune_config.py Show resolved Hide resolved
llm_on_ray/finetune/finetune.py Outdated Show resolved Hide resolved
llm_on_ray/finetune/finetune_config.py Outdated Show resolved Hide resolved
llm_on_ray/finetune/dpo_funetuing.py Outdated Show resolved Hide resolved
minmingzhu and others added 27 commits July 2, 2024 14:31
Signed-off-by: minmingzhu <[email protected]>
Signed-off-by: minmingzhu <[email protected]>
2. remove debug log
2. add DPO CI

Signed-off-by: minmingzhu <[email protected]>
Signed-off-by: minmingzhu <[email protected]>
Signed-off-by: minmingzhu <[email protected]>
Signed-off-by: minmingzhu <[email protected]>
Signed-off-by: minmingzhu <[email protected]>
Signed-off-by: minmingzhu <[email protected]>
Signed-off-by: minmingzhu <[email protected]>
Signed-off-by: minmingzhu <[email protected]>
 2. update dependencies

Signed-off-by: minmingzhu <[email protected]>
Signed-off-by: minmingzhu <[email protected]>
Signed-off-by: minmingzhu <[email protected]>
Signed-off-by: minmingzhu <[email protected]>
Signed-off-by: minmingzhu <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants