Downloads · 30 days
0
argus-grpo-v1
Dominator07/argus-grpo-v1
argus-grpo-v1 is a machine learning model from Dominator07. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- base model: Qwen/Qwen2.5-0.5B-Instruct - numprompts: 40 - numgenerations: 4 - maxsteps: 60 - lr: 2e-06
Access
Public
Updated Apr 26, 2026
Repo size
506 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors211 MB · 55%
At a glance
- Access
- Public
- Created
- Apr 25, 2026
- Updated
- Apr 26, 2026
- SHA
- 47ec4ce8
Model card
From the Hugging Face model README
Argus training run — v1
- base model:
Qwen/Qwen2.5-0.5B-Instruct - num_prompts: 40
- num_generations: 4
- max_steps: 60
- lr: 2e-06
Source env: https://huggingface.co/spaces/Dominator07/argus
- Created
- Apr 25, 2026
- Updated
- Apr 26, 2026