Commit
•
486bf45
1
Parent(s):
9e6e0e1
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,7 @@ base_model:
|
|
| 17 |
<a href="https://huggingface.co/Nexusflow" target="_blank">Nexusflow HF</a> - <a href="https://discord.gg/HDSVmNAs3y" target="_blank">Nexusflow Discord</a> - <a href="https://nexusflow.ai/blogs/athene-v2" target="_blank">Athene-V2 Blogpost</a>
|
| 18 |
</p>
|
| 19 |
|
|
|
|
| 20 |
|
| 21 |
We introduce Athene-V2-Chat-72B, an open-weights LLM on-par with GPT-4o across benchmarks. It is trained through RLHF with Qwen-2.5-72B-Instruct as base model.
|
| 22 |
Athene-V2-Chat-72B excels in chat, math, and coding. Its sister model, [Athene-V2-Agent-72B](https://huggingface.co/Nexusflow/Athene-V2-Agent), surpasses GPT-4o in complex function calling and agentic applications.
|
|
|
|
| 17 |
<a href="https://huggingface.co/Nexusflow" target="_blank">Nexusflow HF</a> - <a href="https://discord.gg/HDSVmNAs3y" target="_blank">Nexusflow Discord</a> - <a href="https://nexusflow.ai/blogs/athene-v2" target="_blank">Athene-V2 Blogpost</a>
|
| 18 |
</p>
|
| 19 |
|
| 20 |
+
used bnb double quantization
|
| 21 |
|
| 22 |
We introduce Athene-V2-Chat-72B, an open-weights LLM on-par with GPT-4o across benchmarks. It is trained through RLHF with Qwen-2.5-72B-Instruct as base model.
|
| 23 |
Athene-V2-Chat-72B excels in chat, math, and coding. Its sister model, [Athene-V2-Agent-72B](https://huggingface.co/Nexusflow/Athene-V2-Agent), surpasses GPT-4o in complex function calling and agentic applications.
|