Luckily, codebases like NanoGPT or the speedrun completely reset people's expectations. But I couldn't find the same for RL; just training Qwen3-4b locally requires hundreds of entreprise-y packages, many of which glitch out when you get slightly off the beaten path…
OPEN SOURCE
-
100+ Free AI Agents and RAG Tutorials Released
By
–
Stay tuned for more such interesting posts → @Saboo_Shubham_ I have created 100+ AI Agents and RAG tutorials, 100% free and opensource. P.S: Don't forget to star the repo to show your support
-
Unsloth Monkey-Patching Causes Distributed Training Deadlock Issues
By
–
Eventually tracked down the problem to the Unsloth monkey-patching. Distributed runs even with one process fail, but if you use the regular models from transformers and `pef`, trained with `trl` then it doesn't deadlock… Hmm.
-
Kimi K2 Team Open-Sources Tool, Community Urges Full Stack Release
By
–
kimi k2 team opensourced a very cool tool today they should do a kimi opensource week like DeepSeek did and release their entire stack would be so good for the community
-
Free experiment tracking library supports images videos tables metrics
By
–
Our 𝒻𝓇ℯℯ new experiment tracking library now supports logging images, videos, tables, and of course metrics. https://t.co/gEPAE46BBS
— Hugging Face (@huggingface) 10 septembre 2025Our 𝒻𝓇ℯℯ new experiment tracking library now supports logging images, videos, tables, and of course metrics.
-
K2 Think: Open-Source Reasoning Model 20x Faster on Cerebras
By
–
K2 Think is now available and runs fastest on Cerebras Inference at 2,000 TPS on Cerebras – 20x faster than GPU.
— Cerebras (@cerebras) 10 septembre 2025
Launched by @mbzuai and @G42ai, K2 Think is a world leading open-source reasoning model that beats GPT OSS 120B and DeepSeek on math and reasoning. pic.twitter.com/fsRl5QhlaXK2 Think is now available and runs fastest on Cerebras Inference at 2,000 TPS on Cerebras – 20x faster than GPU. Launched by @mbzuai and @G42ai
, K2 Think is a world leading open-source reasoning model that beats GPT OSS 120B and DeepSeek on math and reasoning. -
Motia: Unified Backend Framework for AI Agents
By
–
Finally, a unified backend framework to build and scale AI Agents! Motia is a backend framework that brings together AI Agents, APIs, background jobs, streams and workflows into a single core primitive. 100% Open Source
-
Deploying Tiny Vision Language Models on Jetson Nano
By
–
📢 Getting Started with VLM on Jetson Nano
— Satya Mallick (@LearnOpenCV) 10 septembre 2025
Tiny Vision Language Models (VLMs) like Moondream2, LiquidAI’s LFM2-VL, Apple’s FastVLM, and Huggingface’s SmolVLM2 are bringing vision-language capabilities to the edge. In this tutorial, LearnOpenCV demonstrates how to deploy and run… pic.twitter.com/Rj7aIs4JslGetting Started with VLM on Jetson Nano Tiny Vision Language Models (VLMs) like Moondream2, LiquidAI’s LFM2-VL, Apple’s FastVLM, and Huggingface’s SmolVLM2 are bringing vision-language capabilities to the edge. In this tutorial, LearnOpenCV demonstrates how to deploy and run
-
Training Qwen3 Multi-GPU Setup with Accelerate Library
By
–
Anyone manage to get Qwen3 to train on multiple GPUs using `accelerate`? With a fresh install, I can't get even SFT to work with two 3090s.@UnslothAI The demo notebooks are nice, but a reproducible script known to work would be great, ideally with version dependencies pinned! https://t.co/8FkFpC3pdO
— Alex J. Champandard 🌱 (@alexjc) 10 septembre 2025Anyone manage to get Qwen3 to train on multiple GPUs using `accelerate`? With a fresh install, I can't get even SFT to work with two 3090s. @UnslothAI The demo notebooks are nice, but a reproducible script known to work would be great, ideally with version dependencies pinned!
-
Salesforce Leverages Open Source Models for Advanced AI Research Agent
By
–
Interesting example of how open weights models provide opportunities for innovation. Salesforce builds a strong deep research agent from OpenAI’s small open source model. Though open models development is dependent on the good will of OpenAI, Mistral & a few Chinese firms.