DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search
Paper • 2408.08152 • Published • 61
papers
-
-
ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition
Paper • 2402.15220 • Published • 20
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Paper • 2402.19427 • Published • 56Note similar https://huggingface.co/papers/2402.18668
-
Simple linear attention language models balance the recall-throughput tradeoff
Paper • 2402.18668 • Published • 20 -
Linear Transformers are Versatile In-Context Learners
Paper • 2402.14180 • Published • 7 -
Scaling Laws for Fine-Grained Mixture of Experts
Paper • 2402.07871 • Published • 13 -
Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
Paper • 2402.07033 • Published • 19
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
Paper • 2401.18079 • Published • 8Note kinda similar https://arxiv.org/pdf/2402.02750.pdf
-
StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
Paper • 2402.01391 • Published • 43
OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models
Paper • 2402.01739 • Published • 28Note qmoe - https://arxiv.org/pdf/2310.16795.pdf
-
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Paper • 2401.15024 • Published • 73 -
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Paper • 2402.03300 • Published • 142 -
Repeat After Me: Transformers are Better than State Space Models at Copying
Paper • 2402.01032 • Published • 24 -
LongAlign: A Recipe for Long Context Alignment of Large Language Models
Paper • 2401.18058 • Published • 24 -
Can Large Language Models Understand Context?
Paper • 2402.00858 • Published • 24 -
WARM: On the Benefits of Weight Averaged Reward Models
Paper • 2401.12187 • Published • 19 -
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
Paper • 2401.12070 • Published • 45 -
Zero Bubble Pipeline Parallelism
Paper • 2401.10241 • Published • 25 -
Self-Rewarding Language Models
Paper • 2401.10020 • Published • 152 -
Specialized Language Models with Cheap Inference from Limited Domain Data
Paper • 2402.01093 • Published • 47 -
ReFT: Reasoning with Reinforced Fine-Tuning
Paper • 2401.08967 • Published • 31 -
E^2-LLM: Efficient and Extreme Length Extension of Large Language Models
Paper • 2401.06951 • Published • 26 -
Tuning Language Models by Proxy
Paper • 2401.08565 • Published • 22 -
Extending LLMs' Context Window with 100 Samples
Paper • 2401.07004 • Published • 16 -
Secrets of RLHF in Large Language Models Part II: Reward Modeling
Paper • 2401.06080 • Published • 27 -
Efficient LLM inference solution on Intel GPU
Paper • 2401.05391 • Published • 11 -
The Impact of Reasoning Step Length on Large Language Models
Paper • 2401.04925 • Published • 18 -
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
Paper • 2401.04658 • Published • 27 -
Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM
Paper • 2401.02994 • Published • 52 -
Soaring from 4K to 400K: Extending LLM's Context with Activation Beacon
Paper • 2401.03462 • Published • 29 -
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Paper • 2401.01335 • Published • 68 -
LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
Paper • 2401.01325 • Published • 27 -
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
Paper • 2312.15166 • Published • 61 -
PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
Paper • 2312.12456 • Published • 45 -
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
Paper • 2401.15077 • Published • 20 -
OLMo: Accelerating the Science of Language Models
Paper • 2402.00838 • Published • 85 -
Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research
Paper • 2402.00159 • Published • 65 -
Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
Paper • 2402.04248 • Published • 32 -
LiPO: Listwise Preference Optimization through Learning-to-Rank
Paper • 2402.01878 • Published • 20 -
BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
Paper • 2402.04291 • Published • 50 -
Direct Language Model Alignment from Online AI Feedback
Paper • 2402.04792 • Published • 35 -
Hydragen: High-Throughput LLM Inference with Shared Prefixes
Paper • 2402.05099 • Published • 20 -
Model Editing with Canonical Examples
Paper • 2402.06155 • Published • 13 -
SubGen: Token Generation in Sublinear Time and Memory
Paper • 2402.06082 • Published • 11 -
InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning
Paper • 2402.06332 • Published • 19 -
ODIN: Disentangled Reward Mitigates Hacking in RLHF
Paper • 2402.07319 • Published • 14 -
AutoMathText: Autonomous Data Selection with Language Models for Mathematical Texts
Paper • 2402.07625 • Published • 16 -
Suppressing Pink Elephants with Direct Principle Feedback
Paper • 2402.07896 • Published • 11 -
Buffer Overflow in Mixture of Experts
Paper • 2402.05526 • Published • 9 -
Speculative Streaming: Fast LLM Inference without Auxiliary Models
Paper • 2402.11131 • Published • 42 -
Linear Transformers with Learnable Kernel Functions are Better In-Context Models
Paper • 2402.10644 • Published • 81 -
LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
Paper • 2402.11550 • Published • 19 -
BitDelta: Your Fine-Tune May Only Be Worth One Bit
Paper • 2402.10193 • Published • 21 -
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
Paper • 2402.13753 • Published • 116 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 626 -
FuseChat: Knowledge Fusion of Chat Models
Paper • 2402.16107 • Published • 39 -
MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs
Paper • 2402.15627 • Published • 36 -
Do Large Language Models Latently Perform Multi-Hop Reasoning?
Paper • 2402.16837 • Published • 29 -
Orca-Math: Unlocking the potential of SLMs in Grade School Math
Paper • 2402.14830 • Published • 24 -
GPTVQ: The Blessing of Dimensionality for LLM Quantization
Paper • 2402.15319 • Published • 22 -
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
Paper • 2402.14083 • Published • 47 -
TinyLLaVA: A Framework of Small-scale Large Multimodal Models
Paper • 2402.14289 • Published • 20 -
OneBit: Towards Extremely Low-bit Large Language Models
Paper • 2402.11295 • Published • 24 -
AtP*: An efficient and scalable method for localizing LLM behaviour to components
Paper • 2403.00745 • Published • 14 -
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
Paper • 2403.07816 • Published • 44 -
MoAI: Mixture of All Intelligence for Large Language and Vision Models
Paper • 2403.07508 • Published • 77 -
Adding NVMe SSDs to Enable and Accelerate 100B Model Fine-tuning on a Single GPU
Paper • 2403.06504 • Published • 56 -
ReALM: Reference Resolution As Language Modeling
Paper • 2403.20329 • Published • 22 -
sDPO: Don't Use Your Data All at Once
Paper • 2403.19270 • Published • 41 -
Long-form factuality in large language models
Paper • 2403.18802 • Published • 26 -
LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models
Paper • 2403.13372 • Published • 182 -
Evolutionary Optimization of Model Merging Recipes
Paper • 2403.13187 • Published • 58 -
PERL: Parameter Efficient Reinforcement Learning from Human Feedback
Paper • 2403.10704 • Published • 60 -
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 66 -
Pre-training Small Base LMs with Fewer Tokens
Paper • 2404.08634 • Published • 36 -
Dataset Reset Policy Optimization for RLHF
Paper • 2404.08495 • Published • 9 -
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
Paper • 2405.11143 • Published • 41 -
Bootstrapping Language Models with DPO Implicit Rewards
Paper • 2406.09760 • Published • 41 -
Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
Paper • 2408.11039 • Published • 63 -
Learning to Reason under Off-Policy Guidance
Paper • 2504.14945 • Published • 88