microsoft/FastContext-1.0-4B-SFT · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
microsoft/FastContext-1.0-4B-SFT · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
apodex/Apodex-1.0-mini · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Paper page - Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
Join the discussion on this paper page
nvidia/nemotron-3.5-asr-streaming-0.6b · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
PP-OCRv6 - a PaddlePaddle Collection
From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks
DR Tulu: An open, end-to-end training recipe for long-form deep research | Ai2
We introduce Deep Research Tulu (DR Tulu), an open post-training recipe and framework for long-form deep research agents.
Collection
Updated 3mo
Collection of things enabling local-first or very cheap compute based AI usage.
Gemma 4 now runs 2x faster with MTP GGUFs! Run locally on just 6GB RAM. ⚡️ MTP enables Google Gemma 4 run ~1.4–2.2× faster with no accuracy loss. Gemma 4 12B MTP can run at 162 t/s vs. 52 t/s without MTP. 31B reaches 101 t/s. GGUFs + Guide: unsloth.ai/docs/models/mtp
