Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation Paper • 2409.12941 • Published 6 days ago • 12
Moshi v0.1 Release Collection MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi • 13 items • Updated 7 days ago • 179
Training Language Models to Self-Correct via Reinforcement Learning Paper • 2409.12917 • Published 6 days ago • 107
OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs Paper • 2409.05152 • Published 17 days ago • 29
How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data Paper • 2409.03810 • Published 20 days ago • 30
Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning Paper • 2402.10110 • Published Feb 15 • 3
LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA Paper • 2409.02897 • Published 21 days ago • 43
Writing in the Margins: Better Inference Pattern for Long Context Retrieval Paper • 2408.14906 • Published 29 days ago • 137
Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models Paper • 2408.15915 • Published 28 days ago • 19
view article Article Improving Hugging Face Training Efficiency Through Packing with Flash Attention Aug 21 • 20
view article Article Perspectives for first principles prompt engineering By KnutJaegersberg • Aug 18 • 16
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts Paper • 2408.08274 • Published Aug 15 • 11
ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities Paper • 2408.04682 • Published Aug 8 • 14
view article Article 🔥 Argilla 2.0: the data-centric tool for AI makers 🤗 By dvilasuero • Jul 30 • 33
RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation Paper • 2408.02545 • Published Aug 5 • 32
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters Paper • 2408.03314 • Published Aug 6 • 32
OpenDevin: An Open Platform for AI Software Developers as Generalist Agents Paper • 2407.16741 • Published Jul 23 • 67
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases Paper • 2407.12784 • Published Jul 17 • 48
The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism Paper • 2407.10457 • Published Jul 15 • 22
G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment Paper • 2303.16634 • Published Mar 29, 2023 • 3
PAS: Data-Efficient Plug-and-Play Prompt Augmentation System Paper • 2407.06027 • Published Jul 8 • 8
AgentInstruct: Toward Generative Teaching with Agentic Flows Paper • 2407.03502 • Published Jul 3 • 43
Agentless: Demystifying LLM-based Software Engineering Agents Paper • 2407.01489 • Published Jul 1 • 42
PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs Paper • 2406.02886 • Published Jun 5 • 7
Direct Preference Knowledge Distillation for Large Language Models Paper • 2406.19774 • Published Jun 28 • 21
OpenBezoar: Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data Paper • 2404.12195 • Published Apr 18 • 11
Open-Bezoar Collection Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data • 7 items • Updated Apr 19 • 6
CodecLM: Aligning Language Models with Tailored Synthetic Data Paper • 2404.05875 • Published Apr 8 • 16
LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models Paper • 2403.13372 • Published Mar 20 • 58
PERL: Parameter Efficient Reinforcement Learning from Human Feedback Paper • 2403.10704 • Published Mar 15 • 56
ORPO: Monolithic Preference Optimization without Reference Model Paper • 2403.07691 • Published Mar 12 • 59
A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA Paper • 2312.03732 • Published Nov 28, 2023 • 7
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection Paper • 2403.03507 • Published Mar 6 • 182
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM Paper • 2403.07816 • Published Mar 12 • 39
User-LLM: Efficient LLM Contextualization with User Embeddings Paper • 2402.13598 • Published Feb 21 • 18
Instruction-tuned Language Models are Better Knowledge Learners Paper • 2402.12847 • Published Feb 20 • 24
Speculative Streaming: Fast LLM Inference without Auxiliary Models Paper • 2402.11131 • Published Feb 16 • 41
OS-Copilot: Towards Generalist Computer Agents with Self-Improvement Paper • 2402.07456 • Published Feb 12 • 41
ScreenAI: A Vision-Language Model for UI and Infographics Understanding Paper • 2402.04615 • Published Feb 7 • 36
Rethinking Interpretability in the Era of Large Language Models Paper • 2402.01761 • Published Jan 30 • 21
Nomic Embed: Training a Reproducible Long Context Text Embedder Paper • 2402.01613 • Published Feb 2 • 14