---
license: apache-2.0
datasets:
- 5CD-AI/LLaVA-CoT-o1-Instruct
- HuggingFaceM4/the_cauldron
- AnyModal/flickr30k
- openbmb/RLAIF-V-Dataset
base_model:
- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
- google/vit-large-patch32-384
library_name: transformers
pipeline_tag: image-text-to-text
tags:
- vqa
- vlm
---

<p align="center">
  <img src="https://github.com/mkturkcan/deepseek-vlm/blob/main/assets/logo.png?raw=true"  width="180" />
</p>
<h1 align="center">
  <p>mehmetkeremturkcan/DeepSeek-LLaVA-Instruct</p>
</h1>
<h3 align="center">
  <p>DeepSeer: Vision Language Models with Reasoning</p>
</h3>

Vision language models with chain-of-thought reasoning are just starting to emerge. This is a proof-of-concept to train a vision model with thinking-enabled chat templates based on DeepSeek-R1 models.

Note that this model will not always use thinking tokens, due to the current lack of high-quality CoT data in non-science contexts.

## Setup
```bash
pip install git+https://github.com/facebookresearch/schedule_free.git
pip install peft
git clone https://github.com/mkturkcan/seers.git
cd seers/seers/
git clone https://huggingface.co/mehmetkeremturkcan/DeepSeek-LLaVA-Instruct
```
## Test
Run, in the seers/seers folder,
```bash
python predict_llava.py
```

## Train

[seers](https://github.com/mkturkcan/seers) training code is public! Run
```bash
python train_cot_mixed.py
```

## Training Details
This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) on the [5CD-AI/LLaVA-CoT-o1-Instruct](https://huggingface.co/datasets/5CD-AI/LLaVA-CoT-o1-Instruct) dataset.
It has been trained using [seers](https://github.com/mkturkcan/seers).