We just released a massive, pre-processed Wikipedia dataset 🎉 ◆ 42.5M high-quality embeddings ◆ 11 languages ◆ Ready for immediate use Build smart, accurate AI apps users love. 100% free & open-source. Now on Hugging Face.

New LLM update from cohere! 👀 Both Command-R and Command-R+ got an update. > Enhanced multilingual RAG > Better structured data analysis > Improved tool use decision-making > Structured Outputs to improve the accuracy of JSON generations > Better instruction-following

wait, what? cohere just dropped updated Command R plus & Command R - built for RAG and tool use, multilingual (23 languages), grounded generation, 128K content and much more! 🔥 > Command R Plus - 104B param, Command R - 35B param > up-to 2x higher throughput & 2x lower latency

📔 How to fine-tune an LLM locally in 1 minute 💭 using Roller Coaster Tycoon peep thoughts as an example

For anyone wondering which model this is, it’s Depth Anything v2 available in the Transformers library, contributed by yours truly huggingface.co/docs/transform…

New domain! 🤗 Huggingface.com

We're soo back! Last week was a packed week in Open Source AI: 1. Cartesia dropped Rene 1.3 B a smol Mamba2 based LLM that beats Apple OpenELM, and much more, along with custom MLX, Apache 2.0 licensed. 2. cohere released Command R plus & Command R - built for RAG and tool

How to train your own Flux LoRA on Hugging Face: the easiest guide on lora training guide on twitter. In this thread, I'll show you how you can train your own flux lora on Hugging Face for all kinds of style, person, animals, etc. 1/N

If you have a Hugging Face account, you can contribute here: davanstrien-my-argilla.hf.space/datasets

Cloud AI Tuesday #2: AI Image Generation with FLUX on Google Cloud Vertex AI! 🖼️ FLUX is the latest and best open text-to-image models from Black Forest Labs! Flux comes in 3 variants: PRO (requires licensing), DEV (NC open weights), and SCHNELL (Apache 2.0). All 3 models outperform

Party with Hugging Face at the PyTorch Conference! 🎉 Join us Thursday, Sept 19th (5:30 pm - 8:00 pm) at Fort Mason, SF, for free food/drinks & fun. 👀 📅 September 19th (5:30 pm - 8:00 pm) 📍Fort Mason, San Francisco ✅ Be registered for the PyTorch Summit. 🤗 Join this

Run Gemma 2, Llama 3.1, Mixtral, Cohere and other major open LLMs at the touch of your terminal - free of cost! 🔥 Powered by HF Inference Endpoints & Text Generation Inference! ⚡ > Chat interface (OAI compliant) > No local GPU required > Swap models instantly > Streaming LLM

OLMoE 1x7B by Ai2 - apache licensed, 64 experts, 8 active - trained on 5T tokens, matches Gemma, Llama in perf, with orders of magnitude faster speed ⚡ > 1.3B Active and 6.9B Total - 5x fewer parameters than the comparative dense model > 64 experts per layer, 8 active

Let's go! 2 new code LLMs were released by Yi-01.AI Yi-Coder 1.5B and 9B under Apache 2.0. Yi-Coder 🚀 🧮 1.5B and 9B as Base and Chat Model with a 128K Context Window 💡Outperforms CodeQwen1.5 7B and CodeGeex4 9B and rivals DeepSeek-Coder 33B. 🥇 Achieves 23.4% pass rate on

Super stoked to announce we are partnering with Truffle Security to help the community secure their tokens 🔐 huggingface.co/blog/trufflese… Details in thread ⤵️

Those AI PCs are here at AGI house - invite your smartest AI friends to come hack on device / local LLMs with us this Saturday! RSVP: app.agihouse.org/events/gen-ai-… Cc: Microsoft AI ollama NEXA AI Hugging Face Google DeepMind Cyril Zakka, MD Zack Li 👩‍💻 Paige Bailey

New dedicated Google Cloud documentation is live! 🚀 Everything you need to know on how to use Hugging Face on Google Cloud in one central place, from fine-tuning LLMs on Vertex AI to deploying Embedding models and LLMs on GKE! 🤗 Learn about: 🐳 Hugging Face Deep Learning