AnswerDotAI / AnswerDotAI/ModernBERT

HuggingFace loss implementation

Open
#206 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
1.7k
Forks
145
PR merge metrics
No merged PRs in 30d

Description

Hello, is there any reason why HuggingFace classes don't use the flash attention cross entropy loss implementation?

Contributor guide

No contributing guide indexed for this repository

Research direction

Locate the HuggingFace classes and the existing flash attention cross entropy loss implementation, then compare how losses are currently wired. Done would require a maintainer decision on whether to switch implementations, followed by an agreed code change and tests.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
machine-learning
Issue type
Refactor
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.