Recent Posts

• How I Use LLMs to Write
  by victormustaron 6/5/2025, 1:04:18 PM with 5 comments
• Tiny Agents in Python: an MCP-powered agent in ~70 lines of code
  by victormustaron 5/23/2025, 1:35:51 PM with 0 comments
• An MCP-powered agent in 50 lines of code
  by victormustaron 5/15/2025, 9:54:15 PM with 1 comment
• The 4 Things the Qwen-3's Chat Template Teaches Us
  by victormustaron 5/2/2025, 12:53:34 PM with 0 comments
• Hugging Face acquires open source robot startup Pollen Robotics
  by victormustaron 4/14/2025, 1:17:49 PM with 0 comments
• Gemini Co-Drawing: Doodle on a Canvas with Google Gemini 2.0
  by victormustaron 3/19/2025, 6:44:38 PM with 1 comment
• Mistral Small 3.1: the best model in its weight class
  by victormustaron 3/17/2025, 4:16:23 PM with 3 comments
• From Chunks to Blocks: Accelerating Uploads and Downloads on Hugging Face
  by victormustaron 2/13/2025, 2:56:22 PM with 0 comments
• Janus-Pro: Autoregressive framework unifying multimodal understanding&generation
  by victormustaron 1/27/2025, 4:25:27 PM with 5 comments
• Wayfarer-12B: An open source AI model that lets you fail and die
  by victormustaron 1/16/2025, 11:50:13 PM with 0 comments
• Phi-4 weights have been released under MIT license
  by victormustaron 1/8/2025, 4:10:55 PM with 2 comments
• smolagents: A simple library to build AI agents
  by victormustaron 1/2/2025, 8:05:49 PM with 2 comments
• How to fine-tune open LLMs in 2025 with Hugging Face
  by victormustaron 12/20/2024, 1:56:28 PM with 0 comments
• AI Scaling Laws: Behind the Breakthroughs
  by victormustaron 12/11/2024, 11:08:50 AM with 0 comments
• Show HN: Video Composition Tool Powered by Qwen2.5-Coder and FFmpeg
  by victormustaron 11/24/2024, 9:39:27 PM with 0 comments
• Large Language Models Can Self-Improve in Long-Context Reasoning
  by victormustaron 11/14/2024, 7:43:03 PM with 0 comments
• Transformers.js 3.0 Released with WebGPU Support
  by victormustaron 10/22/2024, 5:35:45 PM with 1 comment
• Janus-1.3B: Unifying Multimodal Understanding and Generation
  by victormustaron 10/18/2024, 12:00:47 PM with 0 comments
• Llama 3.1 Nemotron 70B: Open model closing the gap with GPT-4o and Sonnet-3.5
  by victormustaron 10/16/2024, 1:14:22 PM with 1 comment
• Fake Insects: a game where you have to identify AI-generated insects
  by victormustaron 8/17/2024, 2:50:05 PM with 5 comments
• Idefics3: Open multimodal model based on Llama-3.1-8B
  by victormustaron 8/9/2024, 11:20:02 PM with 0 comments
• HuggingChat: Chat with Llama 3.1 405B
  by victormustaron 7/25/2024, 12:42:55 PM with 1 comment
• The Rise of Agentic Data Generation
  by victormustaron 7/15/2024, 10:22:25 AM with 0 comments
• 3D Arena Leaderboard: Evaluate leading generative 3D models
  by victormustaron 6/11/2024, 9:51:41 AM with 0 comments
• The Farmer Was Replaced: Program and optimize a drone to automate a farm
  by victormustaron 5/31/2024, 2:12:09 PM with 1 comment
• Phi-3 in-browser inference using WebGPU
  by victormustaron 5/8/2024, 12:44:24 PM with 0 comments
• Fine-tune Llama 3 with ORPO
  by victormustaron 4/23/2024, 9:15:39 AM with 0 comments
• In-browser text-to-music generation using musicgen-small
  by victormustaron 4/20/2024, 10:15:09 AM with 0 comments
• InstantMesh: Efficient 3D Mesh Generation from a Single Image
  by victormustaron 4/15/2024, 3:48:15 PM with 0 comments
• Transformers.js – Run Transformers directly in the browser
  by victormustaron 4/11/2024, 11:57:46 AM with 11 comments
• DS-Moe: Making Moe Models More Efficient and Less Memory-Intensive
  by victormustaron 4/10/2024, 10:03:36 AM with 0 comments
• LLM DataGen: Generate synthetic datasets with structured text generation
  by victormustaron 4/5/2024, 4:41:50 PM with 0 comments
• C4ai-command-r-v01: 35B parameter highly performant generative model
  by victormustaron 3/13/2024, 3:23:41 PM with 0 comments
• The Stack v2: a 3B files in 600 programming languages dataset
  by victormustaron 3/7/2024, 8:31:34 PM with 0 comments
• GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
  by victormustaron 3/7/2024, 11:46:03 AM with 0 comments
• Design2Code: How Far Are We from Automating Front-End Engineering?
  by victormustaron 3/6/2024, 11:57:48 AM with 0 comments
• Introduction to Matryoshka Embedding Models
  by victormustaron 2/23/2024, 10:17:18 PM with 0 comments
• Fast SDXL: Stable Diffusion XL Lightning Demo
  by victormustaron 2/22/2024, 1:27:27 PM with 1 comment
• HuggingChat: Chat with Open Source Models
  by victormustaron 2/21/2024, 1:33:34 PM with 9 comments
• Training-Free Consistent Text-to-Image Generation
  by victormustaron 2/7/2024, 6:59:52 PM with 0 comments
• On-device background removal with Transformers.js
  by victormustaron 2/7/2024, 12:10:32 PM with 0 comments
• HuggingChat Assistants: Open source models with custom instructions
  by victormustaron 2/2/2024, 4:30:41 PM with 0 comments
• Spotting LLMs with Binoculars: Zero-Shot Detection of Machine-Generated Text
  by victormustaron 1/23/2024, 8:29:35 PM with 19 comments
• InstantID Demo: Zero-Shot Identity-Preserving Generation in Seconds
  by victormustaron 1/22/2024, 5:13:24 PM with 1 comment
• OpenChat: Advancing Open-Source Language Models with Mixed-Quality Data
  by victormustaron 1/15/2024, 12:44:42 PM with 0 comments
• VideoPoet: A large language model for zero-shot video generation
  by victormustaron 12/19/2023, 11:34:22 PM with 0 comments
• AITube - Youtube but everything is AI generated
  by victormustaron 12/15/2023, 9:33:33 PM with 0 comments