Downloads · 30 days
11
15% of all-time downloads
qwen35-4b-dpo-grove-r
Sarim-Hash/qwen35-4b-dpo-grove-r
qwen35-4b-dpo-grove-r is a image-text-to-text model from Sarim-Hash. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers.
Full-parameter GRPO policy with the learned reward model, used as q4b-g2-grove-r in the ICLR persuasion debate experiments.
All-time downloads
72
Public
Parameters
5.2B
10.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors10.4 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- Model type
- qwen3_5
- Access
- Public
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026
- SHA
- f79f5b56
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.5-4B DPO + GROVE-R
Full-parameter GRPO policy with the learned reward model, used as q4b-g2-grove-r in the ICLR persuasion debate experiments.
- Initialization: Winner-v2 DPO
- Artifact: evaluated
finalcheckpoint after 3,000 GRPO steps - Weight file:
model.safetensors - SHA-256:
86591fee8a8021c858f001f0b8ecf7e72666b8dfc69fd2c12be61d7addc8d510 - This is a full fine-tune, not a LoRA adapter.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_5
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026