Downloads · 30 days
9
8% of all-time downloads
Llama-3.2-11B-Vision-Instruct_finetune
sirineddd/Llama-3.2-11B-Vision-Instruct_finetune
Llama-3.2-11B-Vision-Instruct_finetune is a image-text-to-text model from sirineddd. 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 is a fine-tuned vision-language model capable of generating creative, on-brand marketing copy from product images and user prompts. It's based on unsloth/Llama-3.2-11B-Vision-Instruct and has been fine-tuned to u…
All-time downloads
107
Public
Parameters
10.7B
21.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors21.3 GB · 100%
Parameter types
How the weights are stored.
F169.5B · 89%
Try a prompt
Base models
Model card
From the Hugging Face model README
🚀 Marketing Product Caption Generator (Fine-Tuned with Unsloth)
This is a fine-tuned vision-language model capable of generating creative, on-brand marketing copy from product images and user prompts. It's based on unsloth/Llama-3.2-11B-Vision-Instruct and has been fine-tuned to understand product visuals and generate compelling titles, descriptions, and taglines.
🎯 Use Case: Generate high-quality marketing content for e-commerce, social media, or product listings — just provide an image and a short prompt!
📸 Example Input
- Image: A photo of a minimalist water bottle
- User Prompt: "Eco-friendly design for active millennials. Tone: fresh and sustainable."
✍️ Example Output
Title: PureFlow Eco Bottle
Description: Sleek and lightweight, this BPA-free bottle combines modern design with planet-friendly materials. Ideal for workouts, commutes, or everyday hydration.
Tagline: Stay refreshed. Stay responsible.
🧠 Model Details
| Attribute | Value |
|---|---|
| Base Model | unsloth/Llama-3.2-11B-Vision-Instruct |
| Training Framework | Unsloth (LoRA + 4bit fine-tuning) |
| Merged & Saved | Yes (16-bit merged full model) |
| Modality | Vision-to-Text (Multimodal) |
| Use Case | Marketing copy, product descriptions, social media captions |
| License | Apache 2.0 |
Uploaded finetuned model
- Developed by: sirineddd
- 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 28, 2025
- Updated
- Jul 28, 2025