InterconnectsInterconnects Artifacts Hub
withVAILVAIL
All models

MonkeyOCR

byecho840echo840· 05 Jun 2025
MultimodalSpecial purpose

An Apache 2.0 licensed model using a pipeline-based approach to parse PDFs. The small size makes it suitable for edge deployment. Pipeline-based approaches are especially useful for smaller models to eliminate their weaknesses.

Specs
Params1.2B, 3B
LicenseQwen Research License
Tags
models/llmsmodels/llms/multi-modal
Resources
Hugging Face — echo840/MonkeyOCRPaper / tech reportAppeared in Artifacts Log #11
How these metrics work
Adoption · Hugging Face
RAM score
Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.
Hugging Face Downloads
125
last 30d
34.8K
all time
HF Likes
515

Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.

Related Models

Similar Models

Nanonets-OCR-s
NanonetsNanonets10 Jun 2025
multimodal3B params
Qwen2.5-Omni-3B
QwenQwen30 Apr 2025
multimodal3B params
GR00T-N1.5-3B
NVIDIANVIDIA28 May 2025
multimodal3B params
Moondream 2
MoondreamMoondream21 Jun 2025
multimodal1.9B params