← Back to Hugging Face models & datasets

Hugging Face models & datasets

The top 10 hugging face models & datasets measured by RiseFinder over the 7d window ending Week 45 · 2 November 2026.

Period
Weekly
Window
7d
Rows
10
Data through
Week 45 · 2 November 2026
← All current risersAll hugging face models & datasets editionsOlder: Week 44 · 26 October 2026
01/

Weekly box

10 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 ↗
+363.9%
175,841 → 815,793 downloads
02

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 ↗
+314.4%
6,444 → 26,703 downloads
03

ATH-MaaS/OvisOCR3

OvisOCR3 is a unified 0.8B multimodal model designed for OCR and document understanding. This compact model integrates several functions into a single unit. It performs document parsing, general OCR, key information extraction, document figure captioning, and cross-page table reconstruction. These capabilities are selected through task-specific methods.

Hugging Face model

Open source ↗
+134.1%
689 → 1,613 downloads
04

FastVideo/FastH3-Omni-Comfy

FastVideo/FastH3-Omni-Comfy is a set of ComfyUI-ready BF16 and INT8 ConvRot diffusion models from the final FastH3 Omni release. The models generate video together with synchronized audio from a prompt plus an ordered set of image, video, and audio references. They are packaged for use within the ComfyUI workflow tool.

Hugging Face model

Open source ↗
+128%
198,361 → 452,297 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 ↗
+98.1%
3,182 → 6,305 downloads
06

Vyber07/cyber-security

Vyber07/cyber-security is a cybersecurity knowledge base dataset intended for AI training. It covers cybersecurity domains including offensive red teaming, bug bounty exploitation, defensive SOC operations, digital forensics, and AI/LLM security. The dataset is 16 GB in size, contains 507 files, and spans more than 30 domains drawn from more than 15 platforms.

Hugging Face dataset

Open source ↗
+87.3%
4,577 → 8,571 downloads
07

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 ↗
+84.9%
143,152 → 264,723 downloads
08

XingChen-AGI/Xing4.0-29B-Intent-oss

This is a machine learning dataset for intent recognition. It is the companion dataset for Xing4.0-29B-Intent, a model for schema-guided intent recognition and structured information extraction. The dataset was curated and released by the Xingchen General Artificial Intelligence Laboratory of China Telecom Artificial Intelligence Technology Co., Ltd.

Hugging Face dataset

Open source ↗
+76.9%
212 → 375 downloads
09

BreezeBlue/Breeze-TTS-2

Breeze TTS 2 is an open-weight text-to-speech model built for real-time interaction. It supports voice cloning from reference audio, creating voices from natural-language descriptions without reference audio, and steering tone, emotion, pace, and delivery of a cloned voice. The model generates English and Chinese speech, supports inline vocal events such as (laugh) and (sigh), and offers low-latency streaming output. Source code is under the Apache License 2.0, while model weights use a separate non-commercial license.

Hugging Face model

Open source ↗
+54.2%
13,933 → 21,483 downloads
10

bones-studio/seed

bones-studio/seed, also called BONES-SEED (Skeletal Everyday Embodiment Dataset), is an open dataset of 142,220 annotated human motion animations intended for humanoid robotics. It contains motion capture data in SOMA and Unitree G1 formats, along with natural language descriptions, temporal segmentation, and detailed skeletal metadata.

Hugging Face dataset

Open source ↗
+29%
6,578 → 8,485 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.