Victor M

The hugging face CLI is the cheat code for autonomous AI engineering. Ask your agent to finetune a model for japanese, it will autonomously: 1. hf models ls: 11 searches to find Qwen3.5-2B 2. hf datasets info: 8 lookups across 3 Japanese instruction sets 3. hf datasets sql: 23 queries to audit quality (lengths, dedup, translation flags) 4. hf download: pulled model + 3 datasets, curated 4,096 examples from 153K 5. hf upload: adapters + model card pushed to Hub 6. hf buckets sync: artifacts persisted to storage Also it's quite cool because I give my autoresearcher access to the CLI without any other internet browsing capabilities. Feels less contaminating: an agent browsing the web for solutions would defeat the whole purpose of autoresearch (here it's raw data from HF).

Nvidia just crossed Google as the biggest org on @huggingface with 3,881 team members on the hub. I'm officially calling it: Nvidia is the new American king of open-source AI!

NEW SOTA OCR MODEL DROPPED Congrats to @VikParuchuri and team for releasing Chandra OCR 2! - 85.9% on olmocr bench, making it first place 🏆 - 90+ language support - 4B model - Full layout information - Extracts + captions images and diagrams - Strong handwriting, math, form, table support Compare every OCR model on the hub and choose the one adapted to your needs 👇

anthropic bought modern js now openai respond with python ⚔️

3 year anniversary of the moment the whole internet insulted me 😂

Game changer

huggingface now has hardware compatibility indicator when displaying downloadable models. you can add your own in the personal setting. looking forward to test Nemotron 3 Nano 4B on P4. mine mainly mid-consumer GPUs not counting older P4(8), P106-100(6), P620(2), K80(24). AMD 9060xt(16) is not in the options. climbing through GPU poverty ladder.

@Chain_AlphaX and you are a bot 😅

@victormustar free often means *you* are the product, remember that.

now available: DLSS-5 anything for free ⬇️ how do you know you hate it if you dont try it first? Sharing the hugging face demo

bonta-kun now a cat?

We just made it dramatically easier for agents to read trending research papers on HF. Let's go AI powered research!

ScreenSpot-Pro, the GUI computer use benchmark is now on @huggingface 🏆 just added Qwen3.5 it takes 5th place, with specialist Holo2 family takes top ranks whoever builds next GUI model based on Qwen3.5 can top the leaderboard? 🔥

Available for Users and Organizations at: huggingface.co/settings/repos…

NEW on Hugging Face: Repositories overview to understand how you use your storage. 🏙️

With Nemotron 3 Nano 4B in the NVIDIA Nemotron 3 family, llama.cpp users get a compact model for action-taking conversational personas, available across NVIDIA GPU-enabled systems and @NVIDIA_AI_PC

If you like Claude Code or Codex, you should seriously consider running Agents locally as well! The latest small models (like Qwen 3.5) made this a real before/after moment - and the gap keeps closing. Local coding agents are faster, with more reliable tool calling capabilities, still private, and cost $0 in API bills. We made it super easy for you to run a local agent with the 𝚊𝚐𝚎𝚗𝚝𝚜 Hugging Face CLI extension - a one-liner that uses 𝚕𝚕𝚖𝚏𝚒𝚝 to detect your hardware and pick the best model and quant, spins up a 𝚕𝚕𝚊𝚖𝚊.𝚌𝚙𝚙 server, and launches Pi (the agent behind OpenClaw 🦞). One command to find what runs on your hardware and go straight to a working local coding agent! You should give it a try! 👇

💚🤗💚 Jensen showing @huggingface during GTC keynote, where @NVIDIAAI dropped amazing new open models, datasets and blogs! Some of my favorites, links in comments: 🧠 Nemotron 3 Super 120A12B - Reasoning LLM 🏥 Open-H-Embodiment - Healthcare Robotics Dataset 🩻 Cosmos-H-Surgical-Simulator - World Foundation Model 🚕 Alpamayo 1.5 - Autonomous Vehicle Model and Datasets 🕺 Kimodo v1 - Generate body movement from prompts! And SO MUCH MORE to explore at huggingface.co/nvidia/collect…

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: github.com/unslothai/unsl… Blog and Guide: unsloth.ai/docs/new/studio Available now on Hugging Face, NVIDIA, Docker and Colab.

@iamsupersocks something else made for autotraining (using Pi)

@victormustar Connected to Hermes? Or something else?

cool maybe qwen3.5 0.8B can really play doom