Hugging Face models & datasets

The top 5 hugging face models & datasets measured by RiseFinder over the 1d window ending 20 October 2026.

Period
Daily
Window
1d
Rows
5
Data through
20 October 2026
← All current risersAll hugging face models & datasets editionsNewer: 21 October 2026Older: 19 October 2026
01/

Daily box

5 entries
01

openbmb/MiniCPM-V-4.7-1B

MiniCPM-V 4.7 is a vision-language model from the MiniCPM-V series, released in a 1B variant. It handles single-image, multi-image, and video understanding, and combines foundation capabilities with efficient visual encoding and on-device inference, meaning it can run on local devices rather than only in the cloud.

Hugging Face model

Open source ↗
+47.2%
22,689 → 33,388 downloads
02

DeepLethe/FDE-Gym

FDE-Gym is a benchmark dataset for evaluating AI agents on forward-deployed engineering work. It tests whether an agent can enter a customer's running environment, identify what matters there, make job decisions, and ship a system that holds up in production. The dataset contains the original tasks for 20 scenarios, each with an engagement.json file holding the scenario title and related details.

Hugging Face dataset

Open source ↗
+45.3%
203 → 295 downloads
03

openbmb/UltraData-Stack-v3-L2

This is a machine learning dataset containing a selected code corpus of approximately 240 billion tokens covering 11 programming languages from The Stack v3. The data was produced through quality-control cleaning and fine-grained selection using the UltraData-Code-L2-Classifier, applying a language-adaptive L2 selection framework.

Hugging Face dataset

Open source ↗
+16.9%
1,700 → 1,988 downloads
04

jialinyyzz/humanizer-data

jialinyyzz/humanizer-data is a dataset hosted on Hugging Face. It is the training data for humanizer v2, a 12B model that rewrites AI-written drafts in English and Chinese so they read like a person wrote them while keeping every fact. The related code and app are on GitHub, along with step-by-step documentation of how the data was built.

Hugging Face dataset

Open source ↗
+13.3%
332 → 376 downloads
05

AtomicChat/LFM2.5-24B-A2B-Uncensored-GGUF

This is a modified version of the LFM2.5-24B-A2B model in which Liquid's refusal behaviour has been projected out of the original weights, applied in the second two thirds of the network only. It is shipped in two forms: six baked GGUF builds, and a 24 MB LoRA adapter that can be applied to LFM2.5-24B-A2B quants a user already has. The model card states that the measurements behind it are public.

Hugging Face model

Open source ↗
+10.2%
38,809 → 42,767 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.