Downloads · 30 days
36
20% of all-time downloads
Dumpling-Qwen2.5-VL-3B
nbeerbower/Dumpling-Qwen2.5-VL-3B
Dumpling-Qwen2.5-VL-3B is a image-text-to-text model from nbeerbower. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product.
All-time downloads
178
Public
Parameters
3.8B
7.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.5 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Model type
- qwen2_5_vl
- Access
- Public
- Created
- Feb 21, 2025
- Updated
- Feb 23, 2025
- SHA
- ece2ca78
Try a prompt
Base models
Model card
From the Hugging Face model README
Dumpling-Qwen2.5-VL-3B
Shout-out to @huihui-ai for the abliterated model!
huihui-ai/Qwen2.5-VL-3B-Instruct-abliterated finetuned on:
- nbeerbower/GreatFirewall-DPO
- nbeerbower/Schule-DPO
- nbeerbower/Purpura-DPO
- nbeerbower/Arkhaios-DPO
- jondurbin/truthy-dpo-v0.1
- antiven0m/physical-reasoning-dpo
- flammenai/Date-DPO-NoAsterisks
- flammenai/Prude-Phi3-DPO
- Atsunori/HelpSteer2-DPO
- jondurbin/gutenberg-dpo-v0.1
- nbeerbower/gutenberg2-dpo
- nbeerbower/gutenberg-moderne-dpo.
Method
QLoRA ORPO tuned with 2x 3090s for 2 epochs.
- Task
- Image-Text-to-Text
- Type
- qwen2_5_vl
- Languages
- en
- Created
- Feb 21, 2025
- Updated
- Feb 23, 2025