Downloads · 30 days
7
15% of all-time downloads
vqa-rlvr-sft-2b
omnifish123/vqa-rlvr-sft-2b
vqa-rlvr-sft-2b 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
46
Public
Repo size
81.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors69.8 MB · 86%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jul 15, 2026
- Updated
- Jul 15, 2026
- SHA
- d6b08a0c
Base models
Model card
From the Hugging Face model README
sft_2b — LoRA SFT adapter (r=16, LM-only) for Qwen3-VL-2B 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: 79.9 / 62.3 / 99.8 / 79.6
- Reasoning template: 71.8 / 57.9 / 99.8 / 71.3
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-2B-Instruct", dtype="bfloat16")
model = PeftModel.from_pretrained(base, "omnifish123/vqa-rlvr-sft-2b").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