Original model: FireRed-OCR by FireRedTeam Based on: Qwen3-VL-2B-Instruct by Qwen
Fuente del modelo
Extracto de la fuente
Original model: FireRed-OCR by FireRedTeam Based on: Qwen3-VL-2B-Instruct by Qwen
Fuentes
1 fuenteVerificado 20 ago
Artefactos del modelo
1 artefactoExtractos de fuentes
2 extractos--- license: apache-2.0 base_model: - FireRedTeam/FireRed-OCR pipeline_tag: image-to-text --- # FireRed-OCR-exl3 Original model: [FireRed-OCR](https://huggingface.co/FireRedTeam/FireRed-OCR) by [FireRedTeam](https://huggingface.co/FireRedTeam) Based on: [Qwen3-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct) by [Qwen](https://huggingface.co/Qwen) ## Quants [4bpw h6 (main)](https://huggingface.co/cgus/FireRed-OCR-exl3/tree/main) [5bpw h6](https://huggingface.co/cgus/FireRed-OCR-exl3/tree/5bpw-h6) [6bpw h6](https://huggingface.co/cgus/FireRed-OCR-exl3/tree/6bpw-h6) [8bpw h8](https://huggingface.co/cgus/FireRed-OCR-exl3/tree/8bpw-h8) ## Quantization notes Made with Exllamav3 0.0.29. It can be used with TabbyAPI and perhaps Text-Generation-WebUI on Nvidia RTX3xxx or newer GPUs. In my brief testing it seemed to work on English texts with the 4bpw quant in OpenWebUI + TabbyAPI but had some messy tokens sometimes. I think it might require sampler parameters from the original [Qwen3-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct) for better performance. # Original model card <p align="center"> <img src="./assets/logo.png" width="600"/> </p> <p align="center" style="line-height: 1;"> <a href="https://huggingface.co/FireRedTeam" target="_blank"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-FireRedTeam-ffc107?color=ffc107&logoColor=white" style="display: inline-block;"/></a> <a href="https://huggingface.co/FireRedTeam/FireRed-OCR" target="_blank"><img alt="Hugging Face Model" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-FireRed--OCR-red" style="display: inline-block;"/></a> <a href="https://huggingface.co/spaces/FireRedTeam/FireRed-OCR" target="_blank"><img alt="Demo" src="https://img.shields.io/badge/%F0%9F%92%BB%20Demo-FireRed--OCR-red" style="display: inline-block;"/></a> </p> <p align="center" style="line-height: 1;"> 🤗 <a href="https://huggingface.co/FireRedTeam/FireRed-OCR">HuggingFace</a> | 🖥️ <a href="https://huggingface.co/spaces/FireRedTeam/FireRed-OCR"> Demo</a> | 📄 <a href="https://arxiv.org/abs/2603.01840">Technical Report</a> | 🐈 <a href="https://github.com/FireRedTeam/FireRed-OCR">GitHub</a> </p> <p align="center"> <img src="./assets/teaser.png" width="800"/> <br> <em>Figure 1: Performance comparison on the OmniDocBench v1.5 benchmark....
Source context: 13 downloads · 0 likes · Pipeline image-to-text · Repo cgus/FireRed-OCR-exl3