|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
tags: |
|
|
- agent |
|
|
- biology |
|
|
- code |
|
|
base_model: |
|
|
- Qwen/Qwen3-32B |
|
|
--- |
|
|
|
|
|
# Biomni-R0-32B-Preview |
|
|
This repo contains the weights of **Biomni-R0-32B-Preview**, a research preview of the series of biomedical AI agents trained by the [Biomni](https://biomni.stanford.edu/) team. |
|
|
|
|
|
Biomni-R0-Preview is a 32B model trained with end-to-end reinforcement learning using the Biomni-E1 environment scaffolding. It has achieved state-of-the-art performance across ten evaluated biomedical benchmarks spanning diverse tasks including crispr delivery, rare disease diagnosis, gwas variant prioritization, etc. |
|
|
|
|
|
Read more about how the model is trained and evaluted in our [technical report](https://biomni.stanford.edu/blog/biomni-r0-technical-report). |
|
|
|
|
|
<p align="center"> |
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/651d0bf7e4025a389cd24c7a/WMcdZj35W1Bbr-m9Cffw1.png" width="800"/> |
|
|
</p> |
|
|
|
|
|
|
|
|
<p align="center"> |
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/651d0bf7e4025a389cd24c7a/JeZIg7DJIxc8YLfyOVV0t.png" width="800"/> |
|
|
</p> |
|
|
|
|
|
# Usage: Serve with SGLang |
|
|
```bash |
|
|
python -m sglang.launch_server --model-path biomni/Biomni-R0-32B-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":1.0,"original_max_position_embeddings":32768}, "max_position_embeddings": 131072}' |
|
|
``` |
|
|
This would require two GPUs with 80G VRAM. Alternatively, you may serve with 4 GPUs with 40G VRAM via `--tp 4`. |
|
|
|
|
|
Note, if your task would take significantly longer than the original 32768 context length, you may set `rope_scaling` factor to a number `>1.0` and `<=4.0` for smoother context window extension. However, `rope_scaling` might degrade performance on tasks with shorter trajectories. Please tune the rope scaling factor according to your usage. |
|
|
|
|
|
To run inference with the Biomni-E1 environment, please follow the instructions in our [official repo](https://github.com/snap-stanford/biomni). |
|
|
|
|
|
# Citation |
|
|
``` |
|
|
@misc{biomnir0, |
|
|
title = {Biomni-R0: Using RL to Hill-Climb Biomedical Reasoning Agents to Expert-Level}, |
|
|
author = {Ryan Li and Kexin Huang and Shiyi Cao and Yuanhao Qu and Jure Leskovec}, |
|
|
year = {2025}, |
|
|
month = {September}, |
|
|
note = {Technical Report} |
|
|
} |
|
|
``` |
