by Re-Align · Agent Tool · ★ 90
Just-Eval: A fine-grained evaluation of LLM Alignment This is part of the Re-Align project by AI2 Mosaic. Please find more information on our website: https://allenai.github.io/re-align/. Just-Eval-Instruct Dataset 💾 Check out our data on 🤗 Hugging Face: re-align/just-eval-instruct 📊 Check here for the leaderboard: https://allenai.github.io/re-align/justeval.html#leaderboard Data distribution Installation or Setup OpenAI API Key Scoring with Multiple Aspects One-click Helpfulness, Clarity, Factuality, Depth, and Engagement scoremulti
| Stars | 90 |
| Forks | 7 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 71.620128375141/100 |
| Open Issues | 2 |
| Last Updated | 2024-01-29 |
| Created | 2023-11-19 |
| Platforms | python |
| Est. Tokens | ~1201k |
Explore other popular agent tool tools:
just-eval is A simple GPT-based evaluation tool for multi-aspect, interpretable assessment of LLMs.. It is categorized as a Agent Tool with 90 GitHub stars.
just-eval is primarily written in Python. It covers topics such as evaluation, gpt4, llm.
You can find installation instructions and usage details in the just-eval GitHub repository at github.com/Re-Align/just-eval. The project has 90 stars and 7 forks, indicating an active community.
just-eval is released under the MIT license, making it free to use and modify according to the license terms.