Loading...

Tag trends are in beta. Feedback? Thoughts? Email me at [email protected]

Show HN: Chonky – a neural text semantic chunking goes multilingual

The Smol Training Playbook: The Secrets to Building World-Class LLMs

Sentence Transformers is joining Hugging Face

PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Compact VLM

Open source speech foundation model that runs locally on CPU in real-time

You can now use Google Maps as an AI assistant to find places, reviews, etc., for free

Apertus 70B: Truly Open - Swiss LLM by ETH, EPFL and CSCS

I built a Universal File Converter with Gradio & Hugging Face looking for feedback 🚀

Wan2.2-S2V-14B – audio-driven cinematic video generation model

grok-2 on Hugging Face

Qwen Image

LFM2 WebGPU

Qwen3-4B-Thinking-2507

Introducing Pivotal Token Search (PTS): Targeting Critical Decision Points in LLM Training

Unsupervised Model Improvement via Internal Coherence Maximization: Outperforming Human-Supervised Methods Through Self-Elicitation

Implemented the research paper “Memorizing Transformers” from scratch with my own additional modifications in architecture and customized training pipeline .

Beyond Python: AI Agents in JavaScript with KaibanJS

LLM Embeddings Explained: A Visual and Intuitive Guide

Qwen3-Coder-30B-A3B-Instruct

Qwen3 235B beats Claude on some code benchmarks

Qwen3 30B-A3B

Voxtral-Mini-3B-2507 – Open source speech understanding model

Reachy Mini – The Open-Source Robot for Today's and Tomorrow's AI Builders

Qwen3-235B-A22B-Thinking-2507

Qwen3-235B-A22B-Instruct-2507

DeepSeek-TNG-R1T2-Chimera

Smollm3: Smol, multilingual, long-context reasoner LLM

Kyutai 1.6B Streaming TTS

Open Source 1.7tb Dataset of What AI Crawlers Are Doing

DiffuCoder-7B-CpGRPO: A code generation LLM developed by Apple

More →