---
license: mit
pipeline_tag: image-to-text
---
# Mocha Checkpoint for BLIP-Large Model

The official checkpoint of BLIP-Large model, finetuned on MS-COCO with the MOCHa RL framework, introduced in [Mitigating Open-Vocabulary Caption Hallucinations](https://arxiv.org/abs/2312.03631)

[Project Page](https://assafbk.github.io/mocha/)

## Usage

You can use this model for conditional and un-conditional image captioning

### Using the Pytorch model

#### Running the model on CPU

<details>
<summary> Click to expand </summary>

```python
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("moranyanuka/blip-image-captioning-large-mocha")
model = BlipForConditionalGeneration.from_pretrained("moranyanuka/blip-image-captioning-large-mocha")

img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))

# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
```
</details>

#### Running the model on GPU

##### In full precision 

<details>
<summary> Click to expand </summary>

```python
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("moranyanuka/blip-image-captioning-large-mocha")
model = BlipForConditionalGeneration.from_pretrained("moranyanuka/blip-image-captioning-large-mocha").to("cuda")

img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))

# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt").to("cuda")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
```
</details>

##### In half precision (`float16`)

<details>
<summary> Click to expand </summary>

```python
import torch
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("moranyanuka/blip-image-captioning-large-mocha")
model = BlipForConditionalGeneration.from_pretrained("moranyanuka/blip-image-captioning-large-mocha", torch_dtype=torch.float16).to("cuda")

img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda", torch.float16)

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
# >>> a photography of a woman and a dog on the beach

# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
>>> there is a woman and a dog on the beach at sunset
```
</details>

bibtex:
```
@misc{benkish2024mitigating,
      title={Mitigating Open-Vocabulary Caption Hallucinations}, 
      author={Assaf Ben-Kish and Moran Yanuka and Morris Alper and Raja Giryes and Hadar Averbuch-Elor},
      year={2024},
      eprint={2312.03631},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
```