EraX-VL-7B-V2.0-Preview-i1-GGUF Open-source Model - Multiple Quantized Versions Meet Diverse Needs

Erax VL 7B V2.0 Preview I1 GGUF

Developed by mradermacher

This is the result of applying weight/importance matrix quantization to the EraX-VL-7B-V2.0-Preview model, offering multiple quantization versions to suit different needs

Image-to-Text Supports Multiple LanguagesOpen Source License:Apache-2.0 #Multimodal Q&A #Vietnamese OCR #Medical Document Processing

Downloads 246

Release Time : 1/12/2025

Model Overview

A multimodal vision-language model supporting Vietnamese, English, and Chinese, suitable for various document and image understanding tasks

Model Features

Multilingual Support

Native processing capabilities for Vietnamese, English, and Chinese

Multimodal Capabilities

Ability to process both text and visual information for image-text understanding

Multiple Quantization Versions

Offers quantization options ranging from 1-bit to 6-bit to meet different hardware requirements

Document Understanding

Specially optimized for OCR, handwriting recognition, and ancient text processing

Model Capabilities

Optical Character Recognition (OCR)

Handwriting Recognition

Ancient Text Processing

Visual Question Answering

Document Q&A

Multilingual Text Generation

Image Content Understanding

Use Cases

Insurance Industry

Traffic Accident Report Processing

Automatically analyze accident scene images and report texts

Improves claims processing efficiency

Medical Field

Radiology Report Generation

Generate diagnostic reports from medical images

Assists doctors in diagnosis

Ancient Text Digitization

Ancient Text Recognition

Recognize and transcribe characters in ancient texts

Promotes cultural heritage preservation

🚀 EraX-VL-7B-V2.0-Preview

EraX-VL-7B-V2.0-Preview is a multimodal model supporting multiple languages, suitable for various tasks such as insurance, OCR, and question - answering.

🚀 Quick Start

This section provides an overview of the model and how to use its quantized versions.

✨ Features

Multilingual Support: Supports Vietnamese (vi), English (en), and Chinese (zh).
Multimodal Capabilities: Suitable for tasks involving both images and text, like visual question - answering and document question - answering.
Quantized Versions: Various quantized versions are available for different usage scenarios.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

No code examples are provided in the original document.

📚 Documentation

About

The weighted/imatrix quants of the model are based on https://huggingface.co/erax-ai/EraX-VL-7B-V2.0-Preview. Static quants are available at https://huggingface.co/mradermacher/EraX-VL-7B-V2.0-Preview-GGUF.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi - part files.

Provided Quants

(sorted by size, not necessarily quality. IQ - quants are often preferable over similar sized non - IQ quants)

Link	Type	Size/GB	Notes
GGUF	i1 - IQ1_S	2.0	for the desperate
GGUF	i1 - IQ1_M	2.1	mostly desperate
GGUF	i1 - IQ2_XXS	2.4
GGUF	i1 - IQ2_XS	2.6
GGUF	i1 - IQ2_S	2.7
GGUF	i1 - IQ2_M	2.9
GGUF	i1 - Q2_K_S	2.9	very low quality
GGUF	i1 - Q2_K	3.1	IQ3_XXS probably better
GGUF	i1 - IQ3_XXS	3.2	lower quality
GGUF	i1 - IQ3_XS	3.4
GGUF	i1 - Q3_K_S	3.6	IQ3_XS probably better
GGUF	i1 - IQ3_S	3.6	beats Q3_K*
GGUF	i1 - IQ3_M	3.7
GGUF	i1 - Q3_K_M	3.9	IQ3_S probably better
GGUF	i1 - Q3_K_L	4.2	IQ3_M probably better
GGUF	i1 - IQ4_XS	4.3
GGUF	i1 - IQ4_NL	4.5	prefer IQ4_XS
GGUF	i1 - Q4_0	4.5	fast, low quality
GGUF	i1 - Q4_K_S	4.6	optimal size/speed/quality
GGUF	i1 - Q4_K_M	4.8	fast, recommended
GGUF	i1 - Q4_1	5.0
GGUF	i1 - Q5_K_S	5.4
GGUF	i1 - Q5_K_M	5.5
GGUF	i1 - Q6_K	6.4	practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower - quality quant types (lower is better):

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

🔧 Technical Details

No technical details are provided in the original document.

📄 License

The model is licensed under apache - 2.0.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご