Downloads · 30 days
10
3% of all-time downloads
Ministral-3-3B-OT-Agent
qingy2024/Ministral-3-3B-OT-Agent
Ministral-3-3B-OT-Agent is a image-text-to-text model from qingy2024. 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. The card lists the license as apache-2.0.
<center <img src="https://cdn-uploads.huggingface.co/production/uploads/66d78facde54fea8a009927e/3QvsKhqi8lfvT6jA763ER.png" style="height:50px" </center
All-time downloads
346
Public
Parameters
3.8B
15.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.7 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral3
- Access
- Public
- Created
- Dec 23, 2025
- Updated
- Dec 26, 2025
- SHA
- 66003199
Try a prompt
Base models
Model card
From the Hugging Face model README
<center>
<img src="https://cdn-uploads.huggingface.co/production/uploads/66d78facde54fea8a009927e/3QvsKhqi8lfvT6jA763ER.png" style="height:50px">
</center>
- Developed by: qingy2024
- License: apache-2.0
- Finetuned from model: unsloth/Ministral-3-3B-Instruct-2512
- Dataset: open-thoughts/OpenThoughts-Agent-v1-SFT
- Training Method: 16-bit LoRA with rank 64 / alpha 64. No rslora or loftq.
- Validation Loss: ~0.18, down from 0.22 at 300 steps. I split 5% (761 samples) as validation, other 95% (14,448 samples) as training. Val loss was plateauing so I stopped at 2,104 steps.
- Training Steps: ~2,100 (about 2.32 epochs with 16 batch size)
- Training Ctx Length: 8,192 (no samples were longer than this)
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- mistral3
- License
- apache-2.0
- Languages
- en
- Created
- Dec 23, 2025
- Updated
- Dec 26, 2025