OpenScholar_V1 Collection The set of models, index, data associated with the paper "OpenScholar: Synthesizing Scientific Literature with Retrieval-Augmented LMs". β’ 7 items β’ Updated 3 days ago β’ 13
Qwen2.5-Coder Collection Code-specific model series based on Qwen2.5 β’ 40 items β’ Updated 3 days ago β’ 223
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models Paper β’ 2411.04905 β’ Published 14 days ago β’ 108
RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning Paper β’ 2410.02089 β’ Published Oct 2 β’ 12
PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation Paper β’ 2404.13026 β’ Published Apr 19 β’ 23
AutoTrain: No-code training for state-of-the-art models Paper β’ 2410.15735 β’ Published Oct 21 β’ 57
view article Article Transformers.js v3: WebGPU support, new models & tasks, and more⦠about 1 month ago ⒠63
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding Paper β’ 2404.16710 β’ Published Apr 25 β’ 74
Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers Paper β’ 2408.06195 β’ Published Aug 12 β’ 61
Gemma-APS Release Collection Gemma models for text-to-propositions segmentation. The models are distilled from fine-tuned Gemini Pro model applied to multi-domain synthetic data. β’ 3 items β’ Updated Oct 15 β’ 19
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization Paper β’ 2410.08815 β’ Published Oct 11 β’ 42