Reward Modeling Finetuning Example #10827
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
qiyuangong
reviewed
Apr 22, 2024
python/llm/example/GPU/LLM-Finetuning/RewardModeling/reward_modeling_finetuning.py
Show resolved
Hide resolved
qiyuangong
reviewed
Apr 22, 2024
| model = AutoModelForSequenceClassification.from_pretrained( | ||
| model_config.model_name_or_path, num_labels=1, **model_kwargs | ||
| ) | ||
| model = optimize_model(model, low_bit="fp4") |
There was a problem hiding this comment.
Add comments about what we are doing
qiyuangong
reviewed
Apr 22, 2024
qiyuangong
reviewed
Apr 22, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This is an example of TRL reward modeling, a kind of RLHF, where uses dataset Anthropic/hh-rlhf that on our whitelist.
1. Why the change?
Enable RM on Intel GPU with IPEX LLM.
2. User API changes
no
3. Summary of the change
Reward Modeling Finetuning Example
4. How to test?