Downloads · 30 days
6
15% of all-time downloads
vqa-rlvr-sft-8b
omnifish123/vqa-rlvr-sft-8b
vqa-rlvr-sft-8b is a machine learning model from omnifish123. Use it for the machine 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 apache-2.0.
Part of vqa-rlvr: post-training Qwen3-VL for visual question answering on a single RTX 4090 (QLoRA SFT + GRPO with verifiable rewards).
All-time downloads
39
Public
Repo size
98.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors87.4 MB · 88%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jul 15, 2026
- Updated
- Jul 15, 2026
- SHA
- f0684f7f
Base models
Model card
From the Hugging Face model README
sft_8b — QLoRA SFT adapter (NF4, r=16) for Qwen3-VL-8B on 40k VQAv2+GQA
Part of vqa-rlvr: post-training Qwen3-VL for visual question answering on a single RTX 4090 (QLoRA SFT + GRPO with verifiable rewards).
Results (full eval sets; VQAv2 / GQA / CLEVR / TextVQA)
- Short template: 83.0 / 63.6 / 92.8 / 85.0
- Reasoning template: 70.2 / 50.8 / 96.2 / 75.4
Metrics: official VQA accuracy (VQAv2/TextVQA), normalized EM (GQA/CLEVR); harness cross-checked against lmms-eval. Full tables, configs, and per-run JSONs: https://github.com/guangboyu/vqa-rlvr.
Usage
from peft import PeftModel
from transformers import AutoModelForImageTextToText
base = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen3-VL-8B-Instruct", dtype="bfloat16")
model = PeftModel.from_pretrained(base, "omnifish123/vqa-rlvr-sft-8b").merge_and_unload()
Training config is in run_config.json in this repo.
- Library
- peft
- License
- apache-2.0
- Created
- Jul 15, 2026
- Updated
- Jul 15, 2026