Downloads · 30 days
0
gdllelf/qwen25-vl-herb-ppo-adapter
qwen25-vl-herb-ppo-adapter is a reinforcement learning model from gdllelf. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as other.
This repository contains the PPO/RL adapter trained after supervised fine-tuning for Vietnamese Medicinal Herb Visual Question Answering.
Downloads · 30 days
0
Access
Public
Updated May 8, 2026
Repo size
57.6 MB
Likes
0
Public
Click a slice to open those files.
.zip57.6 MB · 100%
From the Hugging Face model README
This repository contains the PPO/RL adapter trained after supervised fine-tuning for Vietnamese Medicinal Herb Visual Question Answering.
Base model:
Qwen/Qwen2.5-VL-3B-Instruct
Source SFT adapter:
gdllelf/qwen25-vl-herb-qlora-adapter
Adapter file:
final_ppo_adapter.zip
The PPO reward used in the project combines VQA soft accuracy and normalized BERTScore-F1.
Dataset:
gdllelf/vietnamese-medicinal-herb-vqa