small-models-for-glam/synthetic-parsed-names-yaml Viewer โข Updated 10 days ago โข 500k โข 86 โข 2
Applied-Innovation-Center/Karnak-70B-LLAMA-v1.0 Text Generation โข 71B โข Updated 3 days ago โข 177 โข 1
view post Post 7463 We collaborated with NVIDIA to teach you how we made LLM training ~25% faster! ๐Learn how 3 optimizations help your home GPU train models faster:1. Packed-sequence metadata caching2. Double-buffered checkpoint reloads3. Faster MoE routingGuide: https://unsloth.ai/blog/nvidia-collabGitHub: https://github.com/unslothai/unsloth See translation ๐ฅ 19 19 ๐ 4 4 ๐ค 2 2 ๐ 1 1 + Reply
view post Post 2132 Hugging Face MCP Server v0.3.12~~~~~~~~~~~~~~~~~~~~~~~~~~~~The hub_repo_details tool now enables Dataset inspection (view splits, sample rows). See translation ๐ค 3 3 โค๏ธ 2 2 + Reply
Running Agents 22 Build Small Hackathon Registration ๐ค 22 Official app to register for the build-small hackathon
loay/gemma-4-E4B-it-abliterated-en-ar-text-only Text Generation โข 6B โข Updated 12 days ago โข 11
loay/gemma-4-E4B-it-abliterated-en-ar-text-only Text Generation โข 6B โข Updated 12 days ago โข 11
Running Agents 77 Open Universal Arabic Asr Leaderboard ๐ฅ 77 A benchmark for open-source multi-dialect Arabic ASR models
Running 16 Qwen-Scope: Decoding Intelligence, Unleashing Potential ๐ฌ 16 Live SAE feature steering for Qwen3-1.7B
mradermacher/gemma-4-e2b-arabic-english-vision-GGUF Image-Text-to-Text โข 4B โข Updated 12 days ago โข 1.69k โข 2
view article Article Vision Language Models (Better, faster, stronger) +3 merve, sergiopaniego, ariG23498, pcuenq, andito โข May 12, 2025 โข 611
view post Post 10735 Unsloth is now one of the top 10 most followed organizations on Hugging Face. ๐ค๐ฆฅThanks so much for all the support!Our HF page: unsloth See translation 5 replies ยท ๐ค 30 30 ๐ฅ 9 9 โค๏ธ 8 8 ๐ค 5 5 ๐ 5 5 + Reply