yongchanghao
Follow
Stars
Implementation of JPEG-ACT: Accelerating Deep Learning via Transform-based Lossy Compression
A code implementation of AC-GC: Activation Compression with Guaranteed Convergence, in NeurIPS 2021.
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Accessible large language models via k-bit quantization for PyTorch.
[ACL 2024] Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models
This is the official repository for the paper "Flora: Low-Rank Adapters Are Secretly Gradient Compressors" in ICML 2024.
An elegant PyTorch deep reinforcement learning library.
A high-throughput and memory-efficient inference and serving engine for LLMs
A series of large language models trained from scratch by developers @01-ai
MLoRAx is a minimalist library for low-rank adaptation designd to effortlessly enable parameter-efficient training for Transformer-based models based on JAX.
RLHF implementation details of OAI's 2019 codebase
Implementation of Proximal Policy Optimization in Jax+Flax
LMRax is a framework built on JAX to train transformers language models by reinforcement learning, along with the reward model training.
Pytorch2Jax is a small Python library that provides functions that wraps PyTorch models into Jax functions and Flax modules.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"
Official implementation of the ACL 2022 paper "Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization"
The official repo for the paper "Teacher Forcing Recovers Reward Functions for Text Generation"
Some useful scripts to process monolingual or parallel texts.
Your browser's reference manager: automatic paper detection (Arxiv, OpenReview & more), publication venue matching and code repository discovery! Also enhances ArXiv: BibTex citation, Markdown link…
[NeurIPS 2021] Galerkin Transformer: a linear attention without softmax for Partial Differential Equations
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
On the Copying Behaviors of Pre-Training for Neural Machine Translation (Findings of ACL 2021)
Implementation of our paper "Self-training Sampling with Monolingual Data Uncertainty for Neural Machine Translation" to appear in ACL-2021.