Downloads · 30 days
7
18% of all-time downloads
Qwen3-VL-2B-Instruct-SFT-VSI590k-32f-384px
wincentIsMe/Qwen3-VL-2B-Instruct-SFT-VSI590k-32f-384px
Qwen3-VL-2B-Instruct-SFT-VSI590k-32f-384px is a image-text-to-text model from wincentIsMe. 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 SFT of Qwen/Qwen3-VL-2B-Instruct on the VSI590k spatial-reasoning dataset (video inputs sampled at 32 frames, 384px resolution). Vision tower frozen (language/projector tuned); see the -tune-vision-towe…
All-time downloads
39
Public
Parameters
2.4B
4.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.9 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- Model type
- qwen3_vl
- Access
- Public
- Created
- Aug 17, 2026
- Updated
- Aug 17, 2026
- SHA
- 987ec68f
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-VL-2B-Instruct-SFT-VSI590k-32f-384px
Full-parameter SFT of Qwen/Qwen3-VL-2B-Instruct on the VSI590k spatial-reasoning dataset (video inputs sampled at 32 frames, 384px resolution). Vision tower frozen (language/projector tuned); see the -tune-vision-tower variant for the version with the vision tower unfrozen.
- Architecture:
Qwen3VLForConditionalGeneration(model_type: qwen3_vl) - Training: 1 epoch, 2308 steps (DeepSpeed; trained 2026-04, uploaded from cvgl cluster)
- Contents: final consolidated
model.safetensors+ tokenizer/processor configs — ready for inference or continued fine-tuning. Intermediate checkpoints and optimizer states are not included.
from transformers import AutoModelForImageTextToText, AutoProcessor
model = AutoModelForImageTextToText.from_pretrained("wincentIsMe/Qwen3-VL-2B-Instruct-SFT-VSI590k-32f-384px")
processor = AutoProcessor.from_pretrained("wincentIsMe/Qwen3-VL-2B-Instruct-SFT-VSI590k-32f-384px")
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_vl
- Created
- Aug 17, 2026
- Updated
- Aug 17, 2026