π§ Reasoning datasets Collection Datasets with reasoning traces for math and code released by the community β’ 14 items β’ Updated 2 days ago β’ 101
π©βπ» OlympicCoder Collection Reasoning datasets and models for competitive coding β’ 4 items β’ Updated 2 days ago β’ 8
olmOCR Collection olmOCR is a document recognition pipeline for efficiently converting documents into plain text. olmocr.allenai.org β’ 3 items β’ Updated about 12 hours ago β’ 92
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning Paper β’ 2502.06781 β’ Published Feb 10 β’ 60
NoLiMa: Long-Context Evaluation Beyond Literal Matching Paper β’ 2502.05167 β’ Published Feb 7 β’ 15
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model Paper β’ 2502.02737 β’ Published Feb 4 β’ 203
WildChat-50m Collection All model responses associated with the WildChat-50m paper. β’ 55 items β’ Updated Jan 29 β’ 7
view article Article Mastering Long Contexts in LLMs with KVPress By nvidia and 1 other β’ Jan 23 β’ 64
Financial Sentiment Analysis π²π Collection Financial Sentiment Analysis models I created β’ 3 items β’ Updated Jan 16 β’ 4
Agentless: Demystifying LLM-based Software Engineering Agents Paper β’ 2407.01489 β’ Published Jul 1, 2024 β’ 61
Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP Paper β’ 2408.04303 β’ Published Aug 8, 2024 β’ 20
CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings Paper β’ 2501.01257 β’ Published Jan 2 β’ 50
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference Paper β’ 2412.13663 β’ Published Dec 18, 2024 β’ 135
π FineWeb-Edu Collection FineWeb-Edu datasets, classifier and ablation model β’ 5 items β’ Updated Jun 12, 2024 β’ 13
GEITje 7B Ultra: A Conversational Model for Dutch Paper β’ 2412.04092 β’ Published Dec 5, 2024 β’ 3
Hymba: A Hybrid-head Architecture for Small Language Models Paper β’ 2411.13676 β’ Published Nov 20, 2024 β’ 42