Downloads · 30 days
5
16% of all-time downloads
llama3-biryani-16bit
farzanashaju/llama3-biryani-16bit
llama3-biryani-16bit is a image-text-to-text model from farzanashaju. 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.
This model is a finetuned version of [Unsloth’s Llama-3.2-11B-Vision-Instruct], trained on a structured cooking QA dataset with three difficulty levels:
All-time downloads
31
Public
Parameters
10.7B
48.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors21.3 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- mllama
- Access
- Public
- Created
- Jul 23, 2025
- Updated
- Sep 6, 2025
- SHA
- 89cc0698
Try a prompt
Base models
Model card
From the Hugging Face model README
Llama-3.2-Biryani
Model Description
This model is a finetuned version of [Unsloth’s Llama-3.2-11B-Vision-Instruct], trained on a structured cooking QA dataset with three difficulty levels:
- Easy – basic cooking questions
- Medium – moderately detailed multi-step reasoning
- HardQA – complex multi-frame reasoning with deeper analysis
The goal of this model is to analyze cooking videos and answer structured questions about them, focusing on Indian biryani preparation.
- Developed by: farzanashaju
- License: apache-2.0
- Finetuned from model: unsloth/llama-3.2-11b-vision-instruct-unsloth-bnb-4bit
This mllama model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- mllama
- License
- apache-2.0
- Languages
- en
- Created
- Jul 23, 2025
- Updated
- Sep 6, 2025