wassname/awesome-rlhf
1
0
Fork 0
mirror of https://github.com/wassname/awesome-rlhf.git synced 2026-06-27 15:14:31 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
wassname
2023-04-29 18:46:58 +08:00
committed by GitHub
parent 0854b025ce
commit bc84df5e38
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -91,7 +91,7 @@ A great way to find new instruction datasets is to
There are multiple ways to formally evaluate LLM capabilities. Right now project generally use one of these 3 libraries. Personally I prefer Eleuther's work, but opinions and github stars are divided.
- python api:
- [huggingface/evaluate](https://github.com/huggingface/evaluate) this is not specific to LLM's or RLHF, but [some](https://github.com/nomic-ai/gpt4all/blob/main/eval_self_instruct.py#L43) [projects](https://github.com/gururise/AlpacaDataCleaned/blob/791174f63e/eval/README.md) find it and easy to use starting point.
- [huggingface/evaluate](https://github.com/huggingface/evaluate) this is not specific to LLM's or RLHF, but some [projects](https://github.com/gururise/AlpacaDataCleaned/blob/791174f63e/eval/README.md) find it and easy to use starting point.
- cli api:
- [EleutherAI/lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) - has lots of datasets like GLUE and ETHICS already included, works with huggingface
- [openai/evals: Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.](https://github.com/openai/evals) - has lots of rare eval sets like sarcasm, works with langchain