---
library_name: transformers
license: apache-2.0
datasets:
- lmms-lab/textvqa
language:
- en
tags:
- multimodal
- vision
- image-text-to-text
---

# Idefics2-8B-SFT

![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/TIxlOOLWmd_k_0grtzejN.jpeg)

Idefics2-8B-SFT is SFT fine-tune of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on 35k [TextVQA dataset](https://huggingface.co/datasets/textvqa). Training was performed on RTX A5000 for 10 hrs. Wandb report:


![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/SjeZW06TBY2RmXPHVzxF1.png)

This fine-tuned model achieves a Levenshtein score of 82.29%.

# Model Summary

- **Developed by:** Hugging Face
- **Model type:** Multi-modal model (image+text)
- **Language(s) (NLP):** en
- **License:** Apache 2.0
- **Parent Models:** [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) and [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)

## 💻 Usage

```python
processor = AutoProcessor.from_pretrained("abideen/idefics2-8b-sft")
model = AutoModelForVision2Seq.from_pretrained(
    "abideen/idefics2-8b-sft",
).to(DEVICE)

# Create inputs
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What do we see in this image?"},
        ]
    },
    {
        "role": "assistant",
        "content": [
            {"type": "text", "text": "In this image, we can see the city of New York, and more specifically the Statue of Liberty."},
        ]
    },
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "And how about this image?"},
        ]
    },       
]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=prompt, images=[image1, image2], return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}


# Generate
generated_ids = model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)

print(generated_texts)
# ['User: What do we see in this image? \nAssistant: In this image, we can see the city of New York, and more specifically the Statue of Liberty. \nUser: And how about this image? \nAssistant: In this image we can see buildings, trees, lights, water and sky.']
```

## 🏆 Evaluation
Coming Soon!