|
|
---
|
|
|
license: apache-2.0
|
|
|
base_model:
|
|
|
- Qwen/Qwen2.5-7B-Instruct
|
|
|
pipeline_tag: text-generation
|
|
|
language:
|
|
|
- zho
|
|
|
- eng
|
|
|
- fra
|
|
|
- spa
|
|
|
- por
|
|
|
- deu
|
|
|
- ita
|
|
|
- rus
|
|
|
- jpn
|
|
|
- kor
|
|
|
- vie
|
|
|
- tha
|
|
|
- ara
|
|
|
---
|
|
|
# Insight-V-Reason
|
|
|
|
|
|
## Model Summary
|
|
|
|
|
|
The Insight-V models are 7B parameter models based on Qwen2.5 language model with a context window of 32K tokens.
|
|
|
|
|
|
Insight-V offers **1)** a scalable data generation pipeline for long-chain, high-quality reasoning data, **2)** a multi-agent system that decomposes visual reasoning tasks into reasoning and summarization, and **3)** a two-stage training pipeline to enhance visual reasoning capabilities. Together, these contributions address key challenges in visual reasoning, providing a solid foundation for future research in MLLM reasoning.
|
|
|
|
|
|
- **Repository:** https://github.com/dongyh20/Insight-V
|
|
|
- **Languages:** English, Chinese
|
|
|
- **Paper:** https://arxiv.org/abs/2411.14432
|
|
|
|
|
|
|
|
|
### Model Architecture
|
|
|
|
|
|
- **Architecture:** Pre-trained [Oryx-ViT](https://huggingface.co/THUdyh/Oryx-ViT) + Qwen2.5-7B
|
|
|
- **Data:** a mixture of 200k reasoning data
|
|
|
- **Precision:** BFloat16
|
|
|
|
|
|
#### Hardware & Software
|
|
|
|
|
|
- **Hardware:** 64 * NVIDIA Tesla A100
|
|
|
- **Orchestration:** HuggingFace Trainer
|
|
|
- **Code:** Pytorch
|
|
|
|
|
|
## Citation |
