RyanLi0802 commited on
Commit
c3825bd
·
verified ·
1 Parent(s): 9a42694

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -31,6 +31,7 @@ Read more about how the model is trained and evaluted in our [technical report](
31
  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}'
32
  ```
33
  This would require two GPUs with 80G VRAM. Alternatively, you may serve with 4 GPUs with 40G VRAM via `--tp 4`.
 
34
  Note, `rope_scaling` might degrade performance on tasks with shorter trajectories. Please tune the rope scaling factor according to your usage.
35
 
36
  To run inference with the Biomni-E1 environment, please follow the instructions in our [official repo](https://github.com/snap-stanford/biomni).
 
31
  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}'
32
  ```
33
  This would require two GPUs with 80G VRAM. Alternatively, you may serve with 4 GPUs with 40G VRAM via `--tp 4`.
34
+
35
  Note, `rope_scaling` might degrade performance on tasks with shorter trajectories. Please tune the rope scaling factor according to your usage.
36
 
37
  To run inference with the Biomni-E1 environment, please follow the instructions in our [official repo](https://github.com/snap-stanford/biomni).