VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models
Scaling model size significantly challenges the deployment and inference of Large Language Models (LLMs). Due to the redundancy in LLM weights, recent research has focused on pushing weight-only quantization to extremely low-bit (even down to 2 bits). It reduces memory requirements, optimizes storage costs, and decreases memory bandwidth needs during inference. However, due to numerical representa
MoRe Fine-Tuning with 10x Fewer Parameters
Parameter-efficient fine-tuning (PEFT) techniques have unlocked the potential to cheaply and easily specialize large pretrained models. However, the most prominent approaches, like low-rank adapters (LoRA), depend on heuristics or rules-of-thumb for their architectural choices -- potentially limiting their performance for new models and architectures. This limitation suggests that techniques from
Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B
This paper introduces the MCT Self-Refine (MCTSr) algorithm, an innovative integration of Large Language Models (LLMs) with Monte Carlo Tree Search (MCTS), designed to enhance performance in complex mathematical reasoning tasks. Addressing the challenges of accuracy and reliability in LLMs, particularly in strategic and mathematical reasoning, MCTSr leverages systematic exploration and heuristic s
Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design
Combining discrete and continuous data is an important capability for generative models. We present Discrete Flow Models (DFMs), a new flow-based model of discrete data that provides the missing link in enabling flow-based generative models to be applied to multimodal continuous and discrete data problems. Our key insight is that the discrete equivalent of continuous space flow matching can be rea
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
GitHub - rasbt/LLMs-from-scratch: Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
Full-Order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-Style Annealing
Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention
Efficient Memory Management for Large Language Model Serving with PagedAttention
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers
Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture
Monarch: Expressive Structured Matrices for Efficient and Accurate Training
Simplified and Generalized Masked Diffusion for Discrete Data
HOT3D Dataset
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
Robust Training of Vector Quantized Bottleneck Models
Diffusion bridges vector quantized Variational AutoEncoders
A Continuous Time Framework for Discrete Denoising Models