Submissions from huggingface.co

		Tokenization Is Killing Our Multilingual LLM Dream (huggingface.co)
		1 point by omneity 7 hours ago \| past \| discuss
		Show HN: I logged 38 days of LLM forecasts to study behavior (huggingface.co)
		2 points by clsia 10 hours ago \| past \| 1 comment
		Cicikus v3 Prometheus 4.4B – An Experimental Franken-Merge for Edge Reasoning (huggingface.co)
		2 points by pthuser 12 hours ago \| past \| discuss
		Open-source dataset of 10 thousand hours of computer-use recordings (huggingface.co)
		2 points by mellosouls 1 day ago \| past \| discuss
		Show HN: Hacker News archive (47M+ items, 11.6GB) as Parquet, updated every 5m (huggingface.co)
		13 points by tamnd 1 day ago \| past \| discuss
		FlashHead: Up to 40% Faster Multimodal Reasoning on Top of Quantization (huggingface.co)
		1 point by Embedl-Wilhelm 2 days ago \| past \| 1 comment
		9B parameter coding agent model fine-tuned on top of Qwen3.5-9B (huggingface.co)
		3 points by brainless 2 days ago \| past \| discuss
		Hugging Face Storage Buckets Storage Bucket (huggingface.co)
		1 point by tamnd 2 days ago \| past \| discuss
		Leaderboard of Leaderboards – A Real-Time Meta-Ranking of AI Benchmarks (huggingface.co)
		3 points by seawolf2357 2 days ago \| past \| discuss
		Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries (huggingface.co)
		2 points by kashifr 3 days ago \| past \| discuss
		Local Agents with Llama.cpp and Pi (huggingface.co)
		5 points by kristianpaul 3 days ago \| past \| discuss
		Nvidia Builds Open Data for AI (huggingface.co)
		2 points by gmays 3 days ago \| past \| discuss
		A Large-Scale Synthetic Dataset Generated from Programming Concept Seeds (huggingface.co)
		2 points by ibobev 3 days ago \| past \| discuss
		Nvidia AI-Q Reached \#1 on DeepResearch Bench I and II (huggingface.co)
		1 point by ibobev 3 days ago \| past \| discuss
		Nvidia Builds Open Data for AI (huggingface.co)
		1 point by ibobev 4 days ago \| past \| discuss
		Reka Edge – 7B fast, efficient VLM (open-weights) (huggingface.co)
		8 points by kwajiehao 4 days ago \| past \| 1 comment
		QORA-LLM-2B – Pure Rust ternary inference, no multiplication needed (huggingface.co)
		3 points by blockmandev 4 days ago \| past \| 1 comment
		Hugging Face Storage Buckets (huggingface.co)
		2 points by lhoestq 4 days ago \| past \| discuss
		Hugging Face Storage Buckets (huggingface.co)
		1 point by nnx 4 days ago \| past \| discuss
		Switch: Benchmarking the Handling of TCIs in Long-Horizon Embodied Scenarios (huggingface.co)
		1 point by tellarin 4 days ago \| past \| discuss
		Hugging Face Storage Buckets: Mutable, non-versioned object storage at $12/TB (huggingface.co)
		18 points by victormustar 5 days ago \| past \| discuss
		Smol AI WorldCup: What Small LLMs Can Do (huggingface.co)
		3 points by seawolf2357 5 days ago \| past \| discuss
		Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries (huggingface.co)
		1 point by ibobev 5 days ago \| past \| discuss
		PRX Part 3 – Training a Text-to-Image Model in 24h (huggingface.co)
		1 point by gsky 5 days ago \| past \| discuss
		LeRobot v0.5.0: Scaling Every Dimension (huggingface.co)
		2 points by ibobev 6 days ago \| past \| discuss
		Ulysses Sequence Parallelism: Training with Million-Token Contexts (huggingface.co)
		1 point by ibobev 6 days ago \| past \| discuss
		Show HN: Wolf Defender, a open-weight prompt-injection detection model (huggingface.co)
		2 points by patronusprotect 6 days ago \| past \| discuss
		MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning (huggingface.co)
		2 points by seawolf2357 6 days ago \| past \| discuss
		Scaling Pedagogical Pre-Training: From Optimal Mixing to 10B Tokens (huggingface.co)
		2 points by codelion 6 days ago \| past \| discuss
		Synthetic Data Playbook (huggingface.co)
		1 point by cjbarber 6 days ago \| past \| discuss
		More