AtlaAI
/

Selene-1-Mini-Llama-3.1-8B

@@ -56,6 +56,10 @@ license: apache-2.0
 # Model Summary
 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**.
 Post-trained from Llama-3.1-8B across a wide range of evaluation tasks and scoring criteria, Selene Mini **outperforms prior small models overall across 11 benchmarks covering three different types of tasks:**
 - Absolute scoring, e.g. "Evaluate the harmlessness of this response on a scale of 1-5"
@@ -64,12 +68,12 @@ Post-trained from Llama-3.1-8B across a wide range of evaluation tasks and scori
 It is also the **#1 8B generative model on [RewardBench](https://huggingface.co/spaces/allenai/reward-bench)**.
-We are launching the large version of this model soon. Sign up [here](https://www.atla-ai.com/sign-up-waitlist?utm_source=huggingface&utm_medium=community&utm_campaign=WL_HF_modelcard_communitypost_sel1minilaunch) to be first to access it.
-<p align="center">
-  <img src="https://atla-ai.notion.site/image/attachment%3A42610fe6-68f0-4c6a-871b-e892736a38a2%3AFig1.png?table=block&id=188309d1-7745-8072-9208-e499cfff9526&spaceId=f08e6e70-73af-4363-9621-90e906b92ebc&width=2000&userId=&cache=v2" width="1000" alt="Centered image">
 </p>
 ## Model Details
 - **Developed by:** [Atla](https://www.atla-ai.com/sign-up-waitlist?utm_source=huggingface&utm_medium=community&utm_campaign=WL_HF_modelcard_communitypost_sel1minilaunch)

 # Model Summary
 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**.
+<p align="left">
+  <img src="https://atla-ai.notion.site/image/attachment%3A42610fe6-68f0-4c6a-871b-e892736a38a2%3AFig1.png?table=block&id=188309d1-7745-8072-9208-e499cfff9526&spaceId=f08e6e70-73af-4363-9621-90e906b92ebc&width=2000&userId=&cache=v2" width="1000" alt="Centered image">
+</p>
 Post-trained from Llama-3.1-8B across a wide range of evaluation tasks and scoring criteria, Selene Mini **outperforms prior small models overall across 11 benchmarks covering three different types of tasks:**
 - Absolute scoring, e.g. "Evaluate the harmlessness of this response on a scale of 1-5"
 It is also the **#1 8B generative model on [RewardBench](https://huggingface.co/spaces/allenai/reward-bench)**.
+<p align="left">
+  <img src="https://atla-ai.notion.site/image/attachment%3A8810826d-8d2d-4038-8746-b4130c23d769%3AWaitlist_image_-_final.png?table=block&id=193309d1-7745-800c-a3f7-f5d038f3e248&spaceId=f08e6e70-73af-4363-9621-90e906b92ebc&width=2000&userId=&cache=v2" width="300" alt="Centered image">
 </p>
+We are launching the large version of this model soon. Sign up [here](https://www.atla-ai.com/sign-up-waitlist?utm_source=huggingface&utm_medium=community&utm_campaign=WL_HF_modelcard_communitypost_sel1minilaunch) to be first to access it.
 ## Model Details
 - **Developed by:** [Atla](https://www.atla-ai.com/sign-up-waitlist?utm_source=huggingface&utm_medium=community&utm_campaign=WL_HF_modelcard_communitypost_sel1minilaunch)