Trending

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

AI, Wikipedia, and uncorrected machine translations of vulnerable languages

Sora might have a 'pervert' problem on its hands

Magic sizes enable high-fidelity assembly of programmable shells

Deepagent: A powerful desktop AI assistant

Creating an Igcse Pseudocode Interpreter

Why can't transformers learn multiplication?

'Attention is all you need' coauthor says he's 'sick' of transformers

When is it better to think without words?

I rebuilt DeepSeek’s OCR model in Rust so anyone can run it locally (no Python!)

Agentic RAG is mostly hype. Here's what I'm seeing.

Operations on Word Vectors - Debiasing solution

Surprising no one, researchers confirm that AI chatbots are incredibly sycophantic | A study confirms they endorse a user’s actions 50 percent more often than humans do.

Fast document extraction library with OCR support

I was an AI scribe-skeptical doctor. And then I actually tried it.

[D] How was Multi-head Latent Attention not a thing before DeepSeek-V2 came up with it?

BBC study finds AI chatbots still get news wrong 45% of the time

Bowel cancer’s “sugar shield” removed to reawaken immune defenses

Qwen

Save item

Qwen3-0.6B

Task: text-generation

Docling

Save item

SmolDocling-256M-preview

Task: image-text-to-text

Qwen

Save item

Qwen3-8B

Task: text-generation

Microsoft

Save item

Phi-4-reasoning-plus

Task: text-generation

Gökdeniz Gülmez

Save item

Josiefied-Qwen3-8B-abliterated-v1

Task: text-generation

Microsoft

Save item

Phi-4-reasoning

Task: text-generation

IBM Granite

Save item

granite-4.0-tiny-preview

Task: text-generation

ByteDance Seed

Save item

UI-TARS-1.5-7B

Task: image-text-to-text

Qwen

Save item

Qwen3-32B

Task: text-generation

langchain-ai

Save item

langchain

🦜🔗 Build context-aware reasoning applications

NVIDIA

Save item

Megatron-LM

Ongoing research training transformer models at scale

snakers4

Save item

silero-vad

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

modelscope

Save item

FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

huggingface

Save item

transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

openai

Save item

openai-cookbook

Examples and guides for using the OpenAI API

run-llama

Save item

llama_index

LlamaIndex is the leading framework for building LLM-powered agents over your data.

EleutherAI

Save item

lm-evaluation-harness

A framework for few-shot evaluation of language models.

Unstructured-IO

Save item

unstructured

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.