README.md

---
language:
- en
pipeline_tag: image-to-text
inference: false
arxiv: 2304.08485
---
# LLaVA Model Card

![image/png](https://cdn-uploads.huggingface.co/production/uploads/62441d1d9fdefb55a0b7d12c/FPshq08TKYD0e-qwPLDVO.png)

Below is the model card of Llava model 13b, which is copied from the original Llava model card that you can find [here](https://huggingface.co/liuhaotian/llava-v1.5-13b).

## Model details

**Model type:**
LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data.
It is an auto-regressive language model, based on the transformer architecture.

**Model date:**
LLaVA-v1.5-13B was trained in September 2023.

**Paper or resources for more information:**
https://llava-vl.github.io/

## How to use the model

First, make sure to have `transformers >= 4.35.3`. 
The model supports multi-image and multi-prompt generation. Meaning that you can pass multiple images in your prompt. Make sure also to follow the correct prompt template (`USER: xxx\nASSISTANT:`) and add the token `<image>` to the location where you want to query images:

### Using `pipeline`:

Below we used [`"llava-hf/llava-1.5-13b-hf"`](https://huggingface.co/llava-hf/llava-1.5-13b-hf) checkpoint.

```python
from transformers import pipeline
from PIL import Image    
import request

model_id = "llava-hf/llava-1.5-13b-hf"
pipe = pipeline("image-to-text", model=model_id)
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg"

image = Image.open(requests.get(url, stream=True).raw)
prompt = "<image>\nUSER: What does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud\nASSISTANT:"

outputs = pipe(image, prompt=prompt, generate_kwargs={"max_new_tokens": 200})
print(outputs)
>>> {"generated_text": "\nUSER: What does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud\nASSISTANT: Lava"}
```

### Using pure `transformers`:

Below is an example script to run generation in `float16` precision on a GPU device:

```python
import requests
from PIL import Image

import torch
from transformers import AutoProcessor, LlavaForConditionalGeneration

model_id = "llava-hf/llava-1.5-13b-hf"

prompt = "<image> \nUSER: What are these?\nASSISTANT:"
image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"

model = LlavaForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True, 
).to(0)


raw_image = Image.open(requests.get(image_file, stream=True).raw)
inputs = processor(prompt, raw_image, return_tensors='pt').to(0, torch.float16)

output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
print(processor.decode(output[0][2:], skip_special_tokens=True))
```

### Model optimization

#### 4-bit quantization through `bitsandbytes` library

First make sure to install `bitsandbytes`, `pip install bitsandbytes` and make sure to have access to a CUDA compatible GPU device. Simply change the snippet above with: 

```diff
model = LlavaForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True,
+   load_in_4bit=True
)
```

#### Use Flash-Attention 2 to further speed-up generation

First make sure to install `flash-attn`. Refer to the [original repository of Flash Attention](https://github.com/Dao-AILab/flash-attention) regarding that package installation. Simply change the snippet above with: 

```diff
model = LlavaForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True,
+   use_flash_attention_2=True
).to(0)
```

## License
Llama 2 is licensed under the LLAMA 2 Community License, 
Copyright (c) Meta Platforms, Inc. All Rights Reserved.