← Back to Hugging Face models & datasets

Hugging Face models & datasets

The top 5 hugging face models & datasets measured by RiseFinder over the 1d window ending 1 November 2026.

Period
Daily
Window
1d
Rows
5
Data through
1 November 2026
← All current risersAll hugging face models & datasets editionsNewer: 2 November 2026Older: 31 October 2026
01/

Daily box

5 entries
01

agibot-world/AgiBotWorld2026

AgiBot World 2026 is a real-world embodied intelligence dataset published on Hugging Face for robotics research. It is collected from real-world environments including commercial spaces and home scenarios using the AGIBOT G2 robot platform in a free-form collection mode, and provides structured, accurately annotated data for developing embodied agents. It is organized as a LeRobot dataset, with Parquet episode files, MP4 video streams per camera, and metadata defined in info.json. Simulation data collected via a digital twin is concurrently open-sourced in the GenieSim project.

Hugging Face dataset

Open source ↗
+254.6%
230,091 → 815,793 downloads
02

LiquidAI/LFM3-Omni-2B

LiquidAI/LFM3-Omni-2B is an AI model that handles multiple kinds of input and output in a single system. It understands text, images, video and audio, and responds in text or speech. It is built for on-device use, replacing what would otherwise require a separate ASR model, vision-language model, LLM and TTS model.

Hugging Face model

Open source ↗
+84.9%
3,080 → 5,695 downloads
03

RecursiveSI/flint

Flint is a mixture-of-experts language model made by Recursive for use with coding agents. It has 39.8 billion total parameters with approximately 2.5 billion active per token. It is designed for software engineering work such as investigating codebases, fixing bugs, implementing features, and writing tests.

Hugging Face model

Open source ↗
+21.4%
19,015 → 23,079 downloads
04

jialinyyzz/humanizer

jialinyyzz/humanizer is a 12B language model that rewrites AI-written drafts such as emails, essays, reports, and forum posts in English and Chinese so they read like a person wrote them. It is trained to keep every number, unit, date, name, and quote from the original text and to add nothing. The model runs locally, and no AI detector was used anywhere in its training.

Hugging Face model

Open source ↗
+8.4%
229,568 → 248,783 downloads
05

hongzhuyi/VDEBench

VDEBench is a bilingual benchmark dataset for visual document editing, containing 3,506 examples split into 1,578 text edits and 1,928 table edits. Each example provides the input document image, an editing instruction, a target image, editing-region annotations, and recorded source provenance. Available masks indicate which regions of a document are allowed for editing.

Hugging Face dataset

Open source ↗
+6.5%
5,770 → 6,145 downloads
This dated edition is generated from the reviewed RiseFinder export. Movement figures retain their original source, period and direction.
02/

Get email updates

Join the list

Get early signals on the websites, apps, repositories and startups gaining momentum. Join the list for Risefinder email briefings.

By subscribing, you ask us to store your email and send Risefinder updates. You can unsubscribe at any time. Privacy.

Want a sample first? Read past daily emails.