Hugging Face

Hugging Face (Twitter) RT @remi_or_: Just opened a PR to make continuous batching in transformers go EVEN faster🚆 With simple optimizations like no torch sync and more GPU-sided operations, we gained 10-14.5% throughput across 500 requests🥳 Soon, there will be native fast RL training in transformers. Keep up 😉

Hugging Face (Twitter) RT @ariG23498: Congrats to all the software that went to space along with this project. @PyTorch@numpy_team@huggingface@OpenAI@wandbhttps://twitter.com/karpathy/status/1998806260783919434#m

‌Hugging Face (Twitter) RT @victormustar: 🎉 llama.cpp now has Ollama-style model management. • Auto-discover GGUFs from cache • Load on first request • Each model runs in its own process • Route by `model` (OpenAI-compatible API) • LRU unload at `--models-max` https://huggingface.co/blog/ggml-org/model-management-in-llamacpp

Hugging Face (Twitter) RT @AdinaYakup: Dolphin-v2 🐬 new document parsing model released by @ByteDanceOSS ✨ 3B - MIT license ✨ Works on any document: PDFs, scans, photos ✨ Understands 21 types of content: text, tables, code, formulas, figures & more ✨ Pixel-level precision via absolute coordinate prediction

Hugging Face (Twitter) RT @latkins: We’re releasing pre-anneal checkpoints for our Nano/Mini base models. Still plenty of math + code exposure, but easier to CPT and customize than our post-anneal checkpoints. Have fun exploring.

Hugging Face (Twitter) RT @essential_ai: The momentum is real. Let's go! 🚀https://twitter.com/ashVaswani/status/1999172792936509796#m

Hugging Face (Twitter) RT @ashVaswani: Rnj-1-Instruct is now the #1 trending text generation model on HF!

Hugging Face (Twitter) RT @ClementDelangue: Even if you don't have a reachy mini (yet!), you can now creates apps thanks to our SDK, API and simulation and share them with the community. If you create simple apps in the coming days, I'll try them on my mini and share a video of them (+ you'll probably get good visibility as we're shipping a large number soon). Some ideas I had: - "What is love" Reachy mini plays "what is love?" and do the classic Jim Carrey head move - "Metronome app": Reachy's antennas turn into a metronome - "Relax app": Reachy plays relaxing music and does some calm zen moves - "Magic 8-Ball" Reachy answers a simple yes/no question by nodding or shaking its head based on a random outcome. - "Peek-a-Boo": Reachy stays hidden until an object (like a hand) gets close, then quickly pops its head up. - "Bless you": Reachy mini says "bless you" when you cough - "Take a picture": Reachy mini takes a picture of you - "Read": Reachy mini reads the paper you show... Перейти на оригинальный пост

Hugging Face (Twitter) RT @mervenoyann: vibe train is here 🚂😄 you can ask Claude to fine-tune vision language models in human terms: "Fine-tune Qwen/Qwen3-VL-3B-Instruct on llava-instruct-mix" 🤯 more details on the next one ⤵️

Hugging Face (Twitter) RT @LysandreJik: 🪦text-generation-inference is now in maintenance mode. Going forward, we will accept pull requests for minor bug fixes, documentation improvements and lightweight maintenance tasks. TGI has initiated the movement for optimized inference engines to rely on a transformers model architectures. This approach is now adopted by downstream inference engines, which we contribute to and recommend using going forward: @vllm_project, @sgl_project, as well as local engines with inter-compatibility such as llama.cpp or MLX.

‌Hugging Face (Twitter) RT @LoubnaBenAllal1: Sharing the slides from a talk I gave this week on bridging the gap between research experiments and building production-ready models, based on our recent Smol Training Playbook. https://docs.google.com/presentation/d/1JlLUwW6cLie6jiByknxcT1WdUb8wBF4gejHLpwH8YnI/edit?usp=sharing

Hugging Face (Twitter) RT @ClementDelangue: They're fine tuning models in space thanks to nanoGPT, HF datasets and tokenizers and you're telling me you can't do it at your organization on Earth? At this point not training your own models is simply a skill issue! https://twitter.com/AdiOltean/status/1998769997431058927#m