Submissions from huggingface.co

		The Ultra-Scale Playbook: Training LLMs on GPU Clusters (huggingface.co)
		33 points by jxmorris12 23 days ago \| past \| 3 comments
		HuggingFace: Accelerating Uploads and Downloads on the Hub (huggingface.co)
		1 point by skadamat 24 days ago \| past \| 1 comment
		SWE-Lancer: Can LLMs Earn $1M from Real-World Freelance Software Engineering? (huggingface.co)
		2 points by gwintrob 24 days ago \| past
		More Efficient Chain-of-Thought Reasoning Through Certainty Probing (huggingface.co)
		6 points by zhisbug 24 days ago \| past \| 2 comments
		Step-Audio-Chat: a 132B end-to-end speech-to-speech model (huggingface.co)
		3 points by cuuupid 25 days ago \| past
		Desklib AI Detector Ranks No 1 on Raid Benchmark for AI Detection (huggingface.co)
		2 points by new-player 25 days ago \| past
		DeepHermes 3: unify reasoning and intuitive language model capabilities (huggingface.co)
		1 point by TheJCDenton 26 days ago \| past
		Forget What You Know about LLMs Evaluations – LLMs Are Like a Chameleon (huggingface.co)
		2 points by wanderr 29 days ago \| past
		From Chunks to Blocks: Accelerating Uploads and Downloads on Hugging Face (huggingface.co)
		1 point by victormustar 29 days ago \| past
		Visualizing Hugging Face Model Deduplication (huggingface.co)
		1 point by skadamat 29 days ago \| past
		The Curse of Depth in Large Language Models (huggingface.co)
		4 points by heyitsguay 29 days ago \| past
		Distil-Whisper (huggingface.co)
		1 point by tosh 30 days ago \| past
		OpenAI o3 just scored 99.8% on CodeForces using brute-force (huggingface.co)
		2 points by wluk 30 days ago \| past \| 1 comment
		Open R1: Update #2 (huggingface.co)
		5 points by simonpure 31 days ago \| past
		Open-source DeepResearch – Freeing our search agents (huggingface.co)
		1 point by belter 31 days ago \| past
		Fine-Tune Deepseek-R1 with a Synthetic Reasoning Dataset (huggingface.co)
		3 points by ororm 31 days ago \| past
		220k reasoning traces from DeepSeek-R1 (huggingface.co)
		1 point by lewtun 31 days ago \| past
		Smolagents, a simple library to build agents (huggingface.co)
		2 points by edublancas 32 days ago \| past
		Hugging Face AI Agents Course (huggingface.co)
		3 points by drones 32 days ago \| past
		FinePersonas (huggingface.co)
		2 points by szermer 32 days ago \| past \| 1 comment
		Deepseek VL2 Small (huggingface.co)
		5 points by hochmartinez 34 days ago \| past
		Fully autonomous AI agents should not be developed (huggingface.co)
		38 points by eamag 35 days ago \| past \| 44 comments
		Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser (huggingface.co)
		227 points by xenova 35 days ago \| past \| 53 comments
		Open-source DeepResearch – Freeing our search agents (huggingface.co)
		7 points by xd1936 35 days ago \| past
		HuggingFace Scientists: Autonomous AI Agents Should Not Be Developed (huggingface.co)
		3 points by jmsflknr 36 days ago \| past
		Open LLM Leaderboard (huggingface.co)
		1 point by palmfacehn 36 days ago \| past
		OpenAI deep research but it's open source (huggingface.co)
		6 points by equilibrium 37 days ago \| past \| 1 comment
		Fine-Tune ModernBERT for RAG with Synthetic Data (huggingface.co)
		1 point by Dowwie 38 days ago \| past
		Open-source DeepResearch – Freeing our search agents (huggingface.co)
		12 points by wseqyrku 38 days ago \| past
		Microsoft Phi 4 with R1 Reasoning (huggingface.co)
		6 points by excsn 38 days ago \| past \| 2 comments
		More