# Yuliang-Liu/Monkey

Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models (CVPR 2024 Highlight)

Repository: https://github.com/Yuliang-Liu/Monkey
Canonical: https://ross.abutalabs.com/products/yuliang-liu-monkey
Language: Python
License: MIT
License Family: permissive
Last push: 2026-06-02T01:58:53+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 85, release rhythm 35, longevity 73
- inputs: {"age_days": 1028, "days_push": 93, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1951, forks 140 (observed 2026-08-28T04:05:58.214328+00:00)

## What it is
Monkey is a large multi-modal model (LMM) research project from CVPR 2024 that improves image understanding via higher input resolution and detailed text labels, with variants like TextMonkey for OCR-free document understanding. It provides training code, model weights, and caption datasets for multimodal vision-language research.

## Use cases
- run a multimodal LLM for image captioning
- understand documents without OCR pipelines
- generate detailed image descriptions
- fine-tune a vision-language model on high-resolution images
- benchmark multimodal models on OCR and VQA tasks

## When to choose
- you need an open multimodal model with strong OCR-free document understanding
- you want research code and pretrained weights for high-resolution image understanding

## When to avoid
- you need a production-ready hosted vision API
- you lack GPU resources for large model inference

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-inference, ocr, image-processing, nlp
- domain: artificial-intelligence, large-language-models, computer-vision, image-processing
- platform: python
- tags: multimodal, vision-language-model, ocr-free, cvpr-2024, model-weights, research, natural-language-processing, gpu, linux

## Member repositories
- Yuliang-Liu/Monkey (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:58.214328+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 2026-08-30T03:06:48.818840+00:00, confidence not recorded.
  - readme: https://github.com/Yuliang-Liu/Monkey (fetched 2026-08-28T04:05:58.214328+00:00, sha 49abe25e7578)
- Data as of 2026-08-30T08:39:29.467469+00:00.