spisupat commited on
Commit
2d15157
Β·
verified Β·
1 Parent(s): a5a3f73

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -39,8 +39,21 @@ license: apache-2.0
39
  />
40
  </picture>
41
  </p>
42
- <p align="center">πŸ› <a href="https://hf.co/spaces/AtlaAI/selene">Selene Mini Playground</a> | πŸ§‘β€βš–οΈ <a href="https://www.atla-ai.com/blog">Atla Blog</a> | πŸ“„ <a href="https://arxiv.org/abs/2501.17195v1">Technical report</a> | πŸ’» <a href="https://github.com/atla-ai">GitHub</a></p>
 
 
 
 
 
 
43
 
 
 
 
 
 
 
 
44
  # Model Summary
45
  Atla Selene Mini is a **state-of-the-art small language model-as-a-judge (SLMJ)**. Selene Mini achieves comparable performance to models 10x its size, **outperforming GPT-4o on [RewardBench](https://huggingface.co/spaces/allenai/reward-bench), EvalBiasBench, and AutoJ**.
46
 
 
39
  />
40
  </picture>
41
  </p>
42
+ <p align="center">
43
+ πŸ› <a href="https://hf.co/spaces/AtlaAI/selene">Playground</a> |
44
+ πŸ§‘β€βš–οΈ <a href="https://www.atla-ai.com/blog">Atla Blog</a> |
45
+ πŸ“„ <a href="https://huggingface.co/spaces/AtlaAI/selene-1-mini-tech-report">Technical report</a> |
46
+ πŸ’» <a href="https://github.com/atla-ai">GitHub</a> |
47
+ πŸ‘€ <a href="https://www.atla-ai.com/sign-up-waitlist?utm_source=huggingface&utm_medium=community&utm_campaign=WL_LI_linkedin_socialpost_sel1minilaunch_waitlistvideo" style="background-image: linear-gradient(to right, red, orange, yellow, green, blue, indigo, violet); -webkit-background-clip: text; color: transparent; animation: rainbow 5s ease infinite; text-decoration: underline; text-decoration-color: currentColor;">Sign up for the API</a>
48
+ </p>
49
 
50
+ <style>
51
+ @keyframes rainbow {
52
+ 0% { background-position: 0% 50%; }
53
+ 50% { background-position: 100% 50%; }
54
+ 100% { background-position: 0% 50%; }
55
+ }
56
+ </style>
57
  # Model Summary
58
  Atla Selene Mini is a **state-of-the-art small language model-as-a-judge (SLMJ)**. Selene Mini achieves comparable performance to models 10x its size, **outperforming GPT-4o on [RewardBench](https://huggingface.co/spaces/allenai/reward-bench), EvalBiasBench, and AutoJ**.
59