AI projects from Hugging Face

Factorial Base 48M Chat

bull220202 · Kit

Runs a chat demo of a small language model called Factorial_IT_ULTIME_TinyLM in the browser on ZeroGPU hardware, with code for running a copy on your own compu…

Text Surprisal Editor

build-small-hackathon · Kit

Colors each word of your text by how unexpected a tiny 4M-parameter language model finds it. The model has no Transformer blocks. A hackathon project for write…

Global Leaders

build-small-hackathon · Kit

Lets you govern a real world leader through the real events of 2025 in a strategy game, with a small language model as game master and a code engine that keeps…

SLM-MiniMax-Continual-Trainer

BRR1154 · Kit

Has a large controller model watch small language model training, name the layers behind a failure and plan weight updates. Aimed at people who train and tune…

EU PII Anonymization

bardsai · Kit

Finds and redacts personal data in text written in any of the 24 EU languages, all inside your browser so the text never leaves your computer. For people who h…

Open Chinese LLM Leaderboard

BAAI · Kit

A leaderboard of large language models for Chinese, run by BAAI as a Gradio Space with datasets for requests and results. For researchers and teams comparing m…

Tamazight Text-to-Speech

ayymen · Kit

Reads Tamazight text aloud with text-to-speech models, with separate folders for several varieties and scripts. For learners, researchers and builders working…

NLLB Translator

Asanari · Kit

Translates text between 200 languages with a choice of engines, from open models running in the Space to cloud models you reach with your own key. For writers,…

Batwan Predictive Text

alsersugasawa · Kit

Suggests the rest of a word, or the next one, as you type in a Hiligaynon-English dictionary search box, using a small fine-tuned Gemma model. A demo for langu…

CCTV Visual RAG

alinawazmahar · Kit

Finds moments in surveillance video by typing a plain-language description, then returns the best-matching frames with their timestamps. For people who would r…

KoGPT2 Korean Finetuning

AD-Styles · Kit

A Gradio app around the skt/kogpt2-base-v2 Korean language model, with its weights held in the Space. For people who want to try a small Korean text model or s…

Local Llm Vram Calculator

abdulrahmanmaslmany · Kit

Estimates the GPU memory a language model needs: weights, KV cache and total VRAM. For people who run models on their own graphics card and want to check the f…

Streamlit Machine Translate

TiberiuCristianLeon · Kit

Translates text between languages in a browser page, with a choice of several open machine translation models. Suits anyone who needs a quick translation, or a…

Qwen3 VL Demo

Qwen · Kit

A Gradio demo from the Qwen team for its Qwen3 VL vision-language family. Runs in your browser, or on your own computer with Python.

Salamtak سلامتك

plitip · Kit

Checks one site photo for safety hazards and gives a Safe, Needs attention or Unsafe verdict with short alerts in seven worker languages. Runs on vision models…

Icelandic LLM Leaderboard

mideind · Kit

Ranks large language models on Icelandic language tasks in a static leaderboard page from Miðeind. It suits people choosing or studying models for Icelandic.

Number Tokenization Blog

huggingface · Kit

A static blog page from Hugging Face on number tokenization, the way language models split numbers into pieces. It suits readers curious about how models handl…

WeVisOne-VL-2B

hugging-apps · Kit

Tries Tencent's WeVisOne-VL-2B vision-language model on images, from finding and counting objects and reading text to cutting out subjects. For developers and…

Saudi SALLM Q9B V1 Demo

Dr-Zeyad-Alghamdi · Kit

Runs a Gradio research demo of a private adapter on the Qwen3.5-9B language model from a browser page, for people who test models on GPU hardware.

Saudi SALLM J7B V1 Demo

Dr-Zeyad-Alghamdi · Kit

Runs a starter Gradio demo around the Jais-3-7B language model from a browser page, for people who want to try an adapter on it on GPU hardware.

Saudi SALLM A7B V1 Demo

Dr-Zeyad-Alghamdi · Kit

Lets you try a research language model adapter on top of ALLaM-7B-Instruct-preview from a browser page, for people who test and compare language models.

ACE Step

ACE-Step · Kit

Generates music from text descriptions and lyrics with the ACE-Step foundation model, in a browser demo. It suits musicians, producers and content creators who…

Open VLM Leaderboard

opencompass · Kit

Shows leaderboards of vision-language model scores gathered with the VLMEvalKit toolkit, with an overall ranking and separate tables for each benchmark. It sui…

Llm Glossary

Omartificial-Intelligence-Space · Kit

A single web page that explains how a language model learns, going through the ideas term by term. Suits newcomers to large language models, students and teach…

Confucius4-TTS Voice Clone

CharlesW · Kit

Clones a voice from a short reference clip and speaks your text in it, with automatic language detection and optional transcription of the clip. It suits peopl…

LLM训练终极指南 | The Ultra-Scale Playbook

Ki-Seki · Kit

A static web page that teaches the many parts of training large language models, with a Chinese title and an English one. It suits engineers and students who w…

Open LLM Leaderboard

open-llm-leaderboard · Kit

Ranks and compares open large language models in a React page with sorting, filtering, search and pinning. For people choosing or evaluating open models and ch…

KLM 1.5-Chat Preview

Eclipse-Senpai · Kit

Chats with a small 99M-parameter language model in the browser, with an optional reasoning mode, a calculator and live web search. It suits people who want to…

OmniVoice

k2-fsa · Kit

Clones a voice and speaks text in it across more than 600 languages, on a Gradio page that runs in the browser. For people who want to try voice cloning text-t…

The Ultra-Scale Playbook

nanotron · Kit

Teaches how to train large language models on big GPU clusters, as a web guide you read in the browser with a PDF copy in its files. For engineers and research…

Ripple-65B Preview

ricursiveAI · Kit

Runs terminal coding agents on a 65B dense language model that reads up to 1,048,576 tokens of context. Made for developers and researchers who want open Apach…