Hugging Face – Posts

Hugging Face Search models, datasets, users... Ctrl K Models Datasets Spaces Buckets Docs Enterprise Pricing Website Tasks HuggingChat Collections Languages Organizations Community Blog Posts Daily Papers Hardware Learn Discord Forum GitHub Solutions Team & Enterprise Hugging Face PRO Enterprise Support Inference Providers Inference Endpoints Storage Buckets Log In Sign Up Join the conversation Join the community of Machine Learners and AI enthusiasts. Sign Up All HF Hub posts Sort: Trending danielhanchen posted an update 2 days ago view post Post 7,227 Today, we're releasing the highest accuracy Qwen3.8-27B GGUFs!Our new Dynamic V3.1 GGUFs lead by 5–10% on average across Terminal Bench, DeepSWE & more. We’re working on an even better version for Qwen4.Run on 12GB RAM setupsGGUF: unsloth/Qwen3.8-27B-GGUFBlog: https://unsloth.ai/docs/models/qwen3.8 See translation 🔥 18 18 ❤️ 9 9 🤯 2 2 🚀 1 1 🤗 1 1 😔 1 1 🧠 1 1 👍 1 1 + Reply VictorSanh posted an update 2 days ago view post Post 5,879 We used weight space programming to bring Qwen 3.5 0.8B from 7.4% to 58.7% on Math 500.Check out the weights!https://huggingface.co/collections/rilixai/weight-space-programming-with-beakerMore details: https://www.withbeaker.ai/blog/weight-space-programming See translation 🔥 12 12 👍 5 5 🤗 2 2 + Reply tomaarsen posted an update 2 days ago view post Post 6,839 🤗 I've released Sentence Transformers v6.3 and wrote a blogpost about its key new feature: token pooling-aware training, teaching multi-vector models to preserve retrieval quality with fewer document vectors. Details:Multi-vector models keep a vector per token, letting different query tokens match different parts of a document. Great for retrieval, but those vectors add up! Token pooling makes the representations smaller by merging similar document vectors into cluster means.Pooling-aware training teaches the encoder to preserve useful matches after those vectors are merged. With MultiVectorTokenPoolingLoss, you can wrap your standard retrieval loss to train on both full and pooled representations, reusing the same token embeddings without another encoder pass. In short: small overhead.I trained two ModernBERT-base models on the same 120k MS MARCO triplets, changing just the loss. At ~49 vectors per document instead of 193, pooling-aware training raises NanoBEIR@13 mean nDCG@10 from 49.03 to 51.23. That's 97.8% of its own unpooled score with ~4x fewer document vectors, compared with 94.6% retention for ordinary training.v6.3 also adds:- Adaptive token budgets, allocating vectors according to each document's content- Matryoshka training for shorter multi-vector token embeddings- Hugging Face kernels support for MaxSim, Ward clustering & supported transformers layers- Native AWS Neuron inferenceYou can combine pooling-aware and Matryoshka training to learn both fewer vectors and fewer dimensions, then stack these with quantization to reduce storage per coordinate. For kernels, install sentence-transformers[kernels] and set use_kernels=True.The blog walks through the method, training code, checkpoints & evaluation, building on Stefan Josef's Learn to Pool and LightOn's pooling regularization work:ht tps://huggingface.co/blog/token-poolingI'd love to see what you train with this! See translation 🔥 12 12 👍 4 4 🤗 1 1 + Reply SeaWolf-AI posted an update about 5 hours ago view post Post 529 🌦️ Which weather model is most accurate? We score them every day, in the open.We released two things on Hugging Face:🏆 Global Weather Model LeaderboardEvery day it records what each global model predicted for 24 world cities, compares it with what actually happened (ERA5), and updates the ranking. ECMWF IFS and AIFS, NOAA GFS and AIGFS, DWD ICON, JMA, ECCC GEM, MET Norway, side by side, on the same cases, since 1 January 2026.Four elements, four tabs: max temperature, min temperature, wind, precipitation. Forecast leads from 1 to 7 days, with 8 to 10 days joining as they are verified.🧬 Darwin-Prediction-WeatherVIDRAFT's weather prediction system: a fusion engine that combines global forecasts, learning only from days already observed. It holds the lowest error in all four elements at every lead on the 2026 record, and the lowest error in all 15 evaluated cells of the WeatherBench 2 (2020) protocol.What the 2026 record shows so far:• AI models now lead physics models at the major centres (AIFS vs IFS, AIGFS vs GFS)• Fusion goes further: 7-day max temperature RMSE 2.09 °C vs 2.41 °C for the next modelAlso inside: yesterday's results with a daily WIN for the closest model, a 10-day outlook for every city, champions by city and by month, and a Live Earth map with wind, clouds, radar and temperature.Every forecast and every observed value is open as CSV, so anyone can check the scores.📖 Article: https://huggingface.co/blog/FINAL-Bench/which-weather-model-is-most-accurate-we-score-them🏆 Leaderboard: FINAL-Bench/Weather-Model-Leaderboard🧬 Model: FINAL-Bench/Darwin-Prediction-Weather📊 Daily record: FINAL-Bench/Weather-Model-Forecast-ArchiveQuestions, corrections and new models to add are welcome. See translation 🚀 17 17 🔥 16 16 👀 6 6 ❤️ 5 5 🤗 4 4 😎 3 3 ➕ 2 2 🧠 2 2 👍 2 2 + Reply sergiopaniego posted an update 3 days ago view post Post 6,735 New post-training example: SFT on agent traces with TRL→ A large model works as a coding agent in OpenCode, run through OpenEnv→ The tasks it solves become the training data→ A 2B model goes from 5.5% to 34.4% on held-out tasksAbout 500 traces get most of the gain. Five times more add only 3 to 4 points, so SFT gets the agent working and RL has to do the restFull guide, with the models, traces and every rollout open:https://github.com/huggingface/trl/tree/main/examples/sft_agent_traces See translation 1 reply · 🔥 11 11 🚀 6 6 + Reply IsValorum posted an update 2 days ago view post Post 1,969 Introducing V-Agent: a local-first AI agent for Windows, built by a quantizer, for quantsVAL-APEX-Mini/Nano/Micro Plus builds get more quality out of consumer GPUs.