TsinghuaAI / TDS
A plug-in of Microsoft DeepSpeed to fix the bug of DeepSpeed pipeline
☆26Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for TDS
- Pretrain CPM-1☆51Updated 3 years ago
- Code for the paper "A Theoretical Analysis of the Repetition Problem in Text Generation" in AAAI 2021.☆51Updated 2 years ago
- Notes of my introduction about NLP in Fudan University☆37Updated 3 years ago
- Code for ACL 2023 paper titled "Lifting the Curse of Capacity Gap in Distilling Language Models"☆28Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆69Updated last year
- Must-read papers on improving efficiency for pre-trained language models.☆102Updated 2 years ago
- A pre-trained model with multi-exit transformer architecture.☆53Updated last year
- BANG is a new pretraining model to Bridge the gap between Autoregressive (AR) and Non-autoregressive (NAR) Generation. AR and NAR generat…☆28Updated 2 years ago
- CFBench: A Comprehensive Constraints-Following Benchmark for LLMs☆25Updated 2 months ago
- Inference framework for MoE layers based on TensorRT with Python binding☆41Updated 3 years ago
- reStructured Pre-training☆97Updated last year
- Repository of LV-Eval Benchmark☆48Updated 2 months ago
- Paradigm shift in natural language processing☆42Updated 2 years ago
- Code for paper 'Data-Efficient FineTuning'☆29Updated last year
- ☆42Updated 3 years ago
- ☆53Updated 2 years ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆76Updated last month
- Scalable PaLM implementation of PyTorch☆192Updated last year
- ☆59Updated last year
- A LLaMA1/LLaMA12 Megatron implement.☆27Updated 11 months ago
- [EMNLP 2022] Training Language Models with Memory Augmentation https://arxiv.org/abs/2205.12674☆194Updated last year
- Source code for paper: Knowledge Inheritance for Pre-trained Language Models☆38Updated 2 years ago
- NTK scaled version of ALiBi position encoding in Transformer.☆67Updated last year
- Pytorch implementation of paper "Efficient Nearest Neighbor Language Models" (EMNLP 2021)☆71Updated 2 years ago
- Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)☆33Updated 11 months ago
- ☆37Updated 2 years ago
- A collection of models built with ColossalAI☆32Updated 2 years ago
- ☆23Updated 2 years ago
- Code for the ACL-2022 paper "StableMoE: Stable Routing Strategy for Mixture of Experts"☆42Updated 2 years ago