Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,28 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- agent
|
| 7 |
+
- biology
|
| 8 |
+
- code
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Biomni-R0-Preview
|
| 12 |
+
This repo contains the weights of **Biomni-R0-Preview**, a research preview of the series of biomedical AI agents trained by the [Biomni](https://biomni.stanford.edu/) team.
|
| 13 |
+
|
| 14 |
+
Biomni-R0-Preview is a 32B model trained with end-to-end reinforcement learning with the Biomni-E1 environment scaffolding. It has achieved state-of-the-art performance across the ten evaluated biomedical tasks.
|
| 15 |
+
|
| 16 |
+
Read more about how the model is trained and evaluted in our [technical report](https://biomni.stanford.edu/blog/biomni-r0-technical-report).
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
# Usage: Serve with SGLang
|
| 25 |
+
```bash
|
| 26 |
+
python -m sglang.launch_server --model-path RyanLi0802/Biomni-R0-Preview --port 30000 --host 0.0.0.0 --mem-fraction-static 0.8 --tp 2 --trust-remote-code --json-model-override-args '{"rope_scaling":{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":32768}, "max_position_embeddings": 131072}
|
| 27 |
+
```
|
| 28 |
+
Note, `rope_scaling` might degrade performance on tasks with shorter trajectories. Please tune the rope scaling factor according to your usage.
|