mlfoundations / mlfoundations/evalchemy
Difference between self.max_tokens self.max_new_tokens in eval_instruct.py
Open
Nobody has claimed this yet.
- Dominant language
- HTML
- Stars
- 610
- Forks
- 87
- PR merge metrics
- No merged PRs in 30d
Description
For some tasks, for example, LiveCodeBench, it use self.max_new_tokens=max_tokens
For other tasks, for example, HumanEval, it use self.max_token=max_tokens
Is there any special consideration on this? or we should unify them instead?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by comparing the linked lines in eval/chat_benchmarks/LiveCodeBench/eval_instruct.py and eval/chat_benchmarks/HumanEval/eval_instruct.py, then trace how max_tokens, max_new_tokens, and max_token are used for generation. Done means the intended distinction is documented and the task implementations consistently follow the decision, with affected evaluations checked.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, testing-qa
- Issue type
- Refactor
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100