AtlasOCR: Building the First Open-Source Darija OCR Model with Vision Language Models Paper β’ 2604.08070 β’ Published 11 days ago β’ 2
Gaming the Answer Matcher: Examining the Impact of Text Manipulation on Automated Judgment Paper β’ 2601.08849 β’ Published Dec 22, 2025 β’ 3
YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation Paper β’ 2601.08441 β’ Published Jan 13 β’ 8
YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation Paper β’ 2601.08441 β’ Published Jan 13 β’ 8
MMTEB: Massive Multilingual Text Embedding Benchmark Paper β’ 2502.13595 β’ Published Feb 19, 2025 β’ 48
view post Post 1296 The #1 trending AI/ML dataset today πMassive scale, diversity and end-to-end potential from nvidia ! nvidia/PhysicalAI-Autonomous-Vehicles See translation π₯ 1 1 + Reply
view post Post 797 The new King πhas arrived! Moonshot AI now the top model on Hugging Face π₯ moonshotai/Kimi-K2-Thinking See translation π₯ 1 1 π€ 1 1 + Reply
view post Post 2860 πΈπ€You donβt need 100 GPUs to train something amazing!Our Smol Training Playbook teaches you a better path to world-class LLMs, for free! Check out the #1 trending space on π€ : HuggingFaceTB/smol-training-playbook See translation π€ 7 7 π 3 3 π₯ 2 2 + Reply
Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR Paper β’ 2511.01937 β’ Published Nov 2, 2025 β’ 16
view post Post 2343 Cool stuff these past weeks on huggingface! π€ π !β’ πTrackio, local-first W&B alternativehttps://github.com/gradio-app/trackio/issuesβ’ πEmbeddingGemma, 300M-param, multilingual embeddings, on-devicehttps://huggingface.co/blog/embeddinggemmaβ’ π»Open LLMs in VS Code (Inference Providers)https://x.com/reach_vb/status/1966185427582497171β’ π€Smol2Operator GUI agentshttps://huggingface.co/blog/smol2operatorβ’ πΌοΈGradio visible watermarkinghttps://huggingface.co/blog/watermarking-with-gradio See translation π₯ 4 4 π€ 3 3 + Reply
Saudi-Dialect-ALLaM: LoRA Fine-Tuning for Dialectal Arabic Generation Paper β’ 2508.13525 β’ Published Aug 19, 2025 β’ 1
Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts Paper β’ 2507.04569 β’ Published Jul 6, 2025 β’ 23
Gazal-R1: Achieving State-of-the-Art Medical Reasoning with Parameter-Efficient Two-Stage Training Paper β’ 2506.21594 β’ Published Jun 18, 2025 β’ 8
Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi Paper β’ 2504.06011 β’ Published Apr 8, 2025 β’ 2
view post Post 962 Great efforts from @AtlasIA folks to adapt text2image models (ghibli style) for Moroccan ContextRead the blog is here : https://huggingface.co/blog/atlasia/creating-your-custom-ghibli-text-to-image-model See translation π 1 1 + Reply
view post Post 7716 πAraClip is now fully integrated with Hugging Face π€AraClip is a specialized CLIP model that was created by @pain and optimized for Arabic text-image retrieval tasksπ₯π Try it out ππ€ model: Arabic-Clip/araclipπ§© Gradio demo: Arabic-Clip/Araclip-Simplifiedπ website: https://arabic-clip.github.io/Arabic-CLIP/ See translation 2 replies Β· π₯ 5 5 β€οΈ 3 3 π 1 1 + Reply