-
Notifications
You must be signed in to change notification settings - Fork 1.8k
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
Scrolls branch #2309
base: main
Are you sure you want to change the base?
Scrolls branch #2309
Conversation
… to the original eval code
…LITY, ContractNLI)
…length Signed-off-by: Wang, Yi <[email protected]>
MMLU task fix
…eTrainedModel instance
[triviaqa] The ground truth must be a *substring* of the generated an…
Sort descending as intended for `greedy_until`
revise huggingface.py
add bnb_4bit_use_double_quant and low_cpu_mem_usage
[Main] updated to new anthropic API
Removes the `_remove_prefixes` optimization as it's invalid for exact match metrics. Closes EleutherAI#726
Update triviaqa.py
…tch-1 Update crowspairs.py higher_is_better
Add CMMLU Benchmark
feature: add vllm interface
Update huggingface.py
fix(scrolls): update load_metric import to use evaluate library Hugging Face moved the load_metric function from the datasets library to the evaluate library. Updated scrolls.py to reflect this change to avoid ImportError.
daishen seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account. You have signed the CLA already but the status is still pending? Let us recheck it. |
Hi! Thanks for this, but can you make another PR with a clean git history? |
fix(scrolls): update load_metric import to use evaluate library
Hugging Face moved the load_metric function from the datasets library to the evaluate library.
Updated scrolls.py to reflect this change to avoid ImportError.