EraX-VL-7B-V2.0-Preview Open-Source Multimodal Model - Supports Multiple Languages to Solve Vision-Language Tasks

Erax VL 7B V2.0 Preview GGUF

Developed by mradermacher

EraX-VL-7B-V2.0-Preview is a multimodal foundation model supporting Vietnamese, English, and Chinese, suitable for various vision-language tasks.

Image-to-Text Supports Multiple LanguagesOpen Source License:Apache-2.0 #Multimodal Visual Question Answering #Vietnamese OCR Processing #Medical Document Parsing

Downloads 162

Release Time : 1/11/2025

Model Overview

This is a 7B-parameter-scale multimodal model focused on vision-language tasks, supporting multiple languages and application scenarios such as insurance, optical character recognition, radiology, etc.

Model Features

Multilingual Support

Supports processing in three languages: Vietnamese, English, and Chinese.

Multimodal Capabilities

Combines vision and language processing abilities, suitable for joint tasks involving images and text.

Multiple Quantized Versions

Offers various quantized versions to accommodate different hardware and performance needs.

Model Capabilities

Image-to-text

Visual Question Answering

Document Question Answering

Handwriting Recognition

Ancient Text Processing

Use Cases

Insurance

Traffic Accident Processing

Used for processing image and text data related to traffic accidents.

Medical

Radiology Analysis

Used for analyzing radiology images and related text reports.

Document Processing

Optical Character Recognition

Used for extracting text information from images.

Handwriting Recognition

Used for recognizing handwritten text.

🚀 EraX-VL-7B-V2.0-Preview

This project provides static quants of the EraX-VL-7B-V2.0-Preview model, supporting multiple languages and offering various quantization types for different usage scenarios.

🚀 Quick Start

If you're new to using this model, the following sections will guide you through its basic information, usage, and available quantizations.

📚 Documentation

About

This is a static quantization of the model from https://huggingface.co/erax-ai/EraX-VL-7B-V2.0-Preview.

Weighted/imatrix quants can be found at https://huggingface.co/mradermacher/EraX-VL-7B-V2.0-Preview-i1-GGUF.

Model Information

Property	Details
Base Model	erax-ai/EraX-VL-7B-V2.0-Preview
Supported Languages	vi, en, zh
Library Name	transformers
License	apache-2.0
Quantized By	mradermacher
Tags	erax, multimodal, erax-vl-7B, insurance, ocr, vietnamese, bcg, radiology, car accidence, hand-writing, ancient, question-answering, image-text-to-text, visual-question-answering, document-question-answering

Usage

If you're unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including 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	mmproj-fp16	1.5	vision supplement
GGUF	Q2_K	3.1
GGUF	Q3_K_S	3.6
GGUF	Q3_K_M	3.9	lower quality
GGUF	Q3_K_L	4.2
GGUF	IQ4_XS	4.4
GGUF	Q4_K_S	4.6	fast, recommended
GGUF	Q4_K_M	4.8	fast, recommended
GGUF	Q5_K_S	5.4
GGUF	Q5_K_M	5.5
GGUF	Q6_K	6.4	very good quality
GGUF	Q8_0	8.2	fast, best quality
GGUF	f16	15.3	16 bpw, overkill

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.

📄 License

This project is licensed under the apache - 2.0 license.

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