# OpenGVLab/InternVL

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o.  接近GPT-4o表现的开源多模态对话模型

Repository: https://github.com/OpenGVLab/InternVL
Canonical: https://ross.abutalabs.com/products/internvl
Homepage: https://internvl.readthedocs.io/en/latest/
Language: Python
License: MIT
License Family: permissive
Topics: image-classification, image-text-retrieval, llm, semantic-segmentation, video-classification, vision-language-model, vit-22b, vit-6b, multi-modal, gpt, gpt-4v, gpt-4o
Last push: 2025-09-22T01:36:48+00:00

## Health v2 (maintenance only)
Score: 37/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 43, release rhythm 8, longevity 72
- inputs: {"age_days": 1015, "days_push": 346, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10146, forks 793 (observed 2026-08-28T04:10:39.674415+00:00)

## What it is
InternVL is a family of open-source multimodal large language models (vision-language models) that combine vision transformers with LLMs to understand images, videos, and text, positioned as an open alternative to GPT-4o. The repository provides model weights, inference code, fine-tuning/training pipelines (including RL-based preference optimization), and evaluation tools.

## Use cases
- run a multimodal chat model that understands images and videos
- fine-tune a vision-language model with LoRA on custom data
- perform image-text retrieval and image classification
- benchmark an open-source alternative to GPT-4o
- deploy a multimodal LLM via API or local demo
- train a multimodal model with reinforcement learning preference optimization

## When to choose
- you need open weights for a state-of-the-art multimodal LLM
- you want to fine-tune or do research on vision-language models
- you need image/video understanding combined with chat in one model
- you want reproducible training and evaluation pipelines for MLLMs

## When to avoid
- you only need text-only LLM inference
- you lack GPU resources for large model inference or training
- you need a lightweight production vision API rather than a full model stack
- you need a non-Python or edge-device deployment

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-inference, llm-training, image-processing, computer-vision, chatbot
- domain: large-language-models, computer-vision, artificial-intelligence, machine-learning, deep-learning
- platform: python, cross-platform
- tags: vision-language-model, multimodal, open-source-weights, fine-tuning, gpt-4o-alternative, vit, image-text-retrieval, semantic-segmentation, gpu, linux

## Member repositories
- OpenGVLab/InternVL (main) score 37

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:39.674415+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:19:41.326165+00:00, confidence not recorded.
  - readme: https://github.com/OpenGVLab/InternVL (fetched 2026-08-28T04:10:39.674415+00:00, sha 3067b7db2fa8)
  - homepage: https://internvl.readthedocs.io/en/latest/ (fetched 2026-08-29T08:19:19.357222+00:00, sha e89e8b2f52ad)
- Data as of 2026-08-30T08:39:29.467469+00:00.