Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
AXERA-TECH
/
Qwen2.5-VL-3B-Instruct
like
1
Follow
AXERA
64
Image-Text-to-Text
Transformers
Safetensors
English
Chinese
Qwen2.5-VL
Qwen2.5-VL-3B-Instruct
Int8
VLM
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
d383d62
Qwen2.5-VL-3B-Instruct
9.89 GB
4 contributors
History:
5 commits
qqc1989
Update README.md
d383d62
verified
8 months ago
image
initial this repo
8 months ago
python
initial this repo
8 months ago
qwen2_5-vl-3b-image-ax650
initial this repo
8 months ago
qwen2_5-vl-3b-video-ax650
update the video models
8 months ago
qwen2_5-vl-tokenizer
initial this repo
8 months ago
.gitattributes
Safe
1.61 kB
update the video models
8 months ago
README.md
7.28 kB
Update README.md
8 months ago
config.json
Safe
0 Bytes
initial this repo
8 months ago
main
Safe
6.6 MB
xet
update the video models
8 months ago
qwen2_tokenizer_image_448.py
Safe
11.9 kB
initial this repo
8 months ago
qwen2_tokenizer_video_308.py
Safe
19.4 kB
update the video models
8 months ago
run_qwen2_5_vl_image.sh
Safe
793 Bytes
initial this repo
8 months ago
run_qwen2_5_vl_video.sh
Safe
790 Bytes
update the video models
8 months ago
