Hugging Face

Hugging Face (Twitter) RT @_lewtun: We've just published the Smol Training Playbook: a distillation of hard earned knowledge to share exactly what it takes to train SOTA LLMs ⚡️ Featuring our protagonist SmolLM3, we cover: 🧭 Strategy on whether to train your own LLM and burn all your VC money 🪨 Pretraining, aka turning a mountain of text into a fancy auto-completer 🗿How to sculpt base models with post-training alchemy 🛠️ The underlying infra and how to debug your way out of NCCL purgatory Highlights from the post-training chapter in the thread 👇

Hugging Face (Twitter) RT @LoubnaBenAllal1: After ~4 years building SOTA models & datasets, we're sharing everything we learned in ⚡The Smol Training Playbook We cover the full LLM cycle: designing ablations, choosing an architecture, curating data, post-training, and building solid infrastructure. We'll help you navigate the messy training reality that LLM papers don't cover. Chapter highlights in the 🧵

Hugging Face (Twitter) RT @ClementDelangue: We’re finally reaching the era of everyone training their own models based on open-source (versus relying on black box generalist APIs) and it is glorious!

‌Hugging Face (Twitter) RT @zpysky1125: MiniMax M2 Tech Blogs on Huggingface: 1. 2. https://huggingface.co/blog/MiniMax-AI/what-makes-good-reasoning-data 3. https://huggingface.co/blog/MiniMax-AI/why-did-m2-end-up-as-a-full-attention-modelhttps://twitter.com/zpysky1125/status/1983383094607347992#m

Hugging Face (Twitter) RT @romainhuet: We’re adding two new models to the gpt-oss family today! With gpt-oss-safeguard, you can apply your own safety policies at inference time and see how the model reasons through them step-by-step. These models are fine-tuned from gpt-oss and available under Apache-2.0. https://twitter.com/OpenAI/status/1983507392374641071#m

‌Hugging Face (Twitter) RT @ClementDelangue: Why are Chinese companies and startups open-sourcing like crazy whereas American ones don't? Where's the open-source AI from @Tinder@RobinhoodApp@NotionHQ@figma@Airbnb@DoorDash@Snapchat@stripe and the hundreds of successful American startups? If they started doing it, in my opinion, it would unleash a phenomenal force (and greatly benefit them)!

Hugging Face (Twitter) RT @multimodalart: Weights are out! 🔥 FIBO is a new open weights high quality 8B image model by @bria_ai_ trained on json prompts! It can generate and modify images with a precisely crafted json prompt, allowing for every detail of the image to be decided Try it here: https://huggingface.co/spaces/briaai/FIBO-demo

Hugging Face (Twitter) RT @MokadyRon: Generating an image from 1,000 words. Very excited to release Fibo 😃, the first ever open-source model trained exclusively on long, structured captions. Fibo sets a new standard for controllability and disentanglement in image generation [1/6] 🧵

‌Hugging Face (Twitter) RT @OpenAI: Now in research preview: gpt-oss-safeguard Two open-weight reasoning models built for safety classification. https://openai.com/index/introducing-gpt-oss-safeguard/

‌Hugging Face (Twitter) RT @OpenAI: gpt-oss-safeguard lets developers use their own custom policies to classify content. The model interprets those policies to classify messages, responses, and conversations. These models are fine-tuned versions of our gpt-oss open models, available under Apache 2.0 license. Now on Hugging Face. https://huggingface.co/collections/openai/gpt-oss-safeguard

‌Hugging Face (Twitter) RT @Xianbao_QIAN: China's open source is just on fire. Soul, China's Tinder (?), has just open sourced their podcast model on @huggingface https://huggingface.co/collections/Soul-AILab/soulx-podcast

Hugging Face (Twitter) RT @RisingSayak: Appeared on a show https://twitter.com/PyTorch/status/1983164400090407213#m