TsinghuaAI / TDSLinks
A plug-in of Microsoft DeepSpeed to fix the bug of DeepSpeed pipeline
☆25Updated 4 years ago
Alternatives and similar repositories for TDS
Users that are interested in TDS are comparing it to the libraries listed below
Sorting:
- Pretrain CPM-1☆53Updated 4 years ago
- Must-read papers on improving efficiency for pre-trained language models.☆105Updated 2 years ago
- Scalable PaLM implementation of PyTorch☆190Updated 2 years ago
- Princeton NLP's pre-training library based on fairseq with DeepSpeed kernel integration 🚃☆114Updated 2 years ago
- DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference☆158Updated 3 years ago
- Code associated with the paper **SkipBERT: Efficient Inference with Shallow Layer Skipping**, at ACL 2022☆16Updated 3 years ago
- A pre-trained model with multi-exit transformer architecture.☆54Updated 2 years ago
- Method to improve inference time for BERT. This is an implementation of the paper titled "PoWER-BERT: Accelerating BERT Inference via Pro…☆62Updated 3 months ago
- Introduction to CPM☆166Updated 3 years ago
- Paradigm shift in natural language processing☆42Updated 3 years ago
- Code for the paper "A Theoretical Analysis of the Repetition Problem in Text Generation" in AAAI 2021.☆54Updated 2 years ago
- Source code for NAACL 2021 paper "TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference"☆47Updated 3 years ago
- ☆53Updated 3 years ago
- [ACL 2022] Structured Pruning Learns Compact and Accurate Models https://arxiv.org/abs/2204.00408☆197Updated 2 years ago
- ☆45Updated 3 years ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆69Updated 2 years ago
- 香侬科技(北京香侬慧语科技有限责任公司)知乎爆料备份☆42Updated 5 years ago
- [KDD'22] Learned Token Pruning for Transformers☆99Updated 2 years ago
- Notes of my introduction about NLP in Fudan University☆37Updated 4 years ago
- reStructured Pre-training☆98Updated 2 years ago
- [EMNLP 2022] Training Language Models with Memory Augmentation https://arxiv.org/abs/2205.12674☆197Updated 2 years ago
- BANG is a new pretraining model to Bridge the gap between Autoregressive (AR) and Non-autoregressive (NAR) Generation. AR and NAR generat…☆28Updated 3 years ago
- Code for ACL 2023 paper titled "Lifting the Curse of Capacity Gap in Distilling Language Models"☆29Updated 2 years ago
- Block Sparse movement pruning☆81Updated 4 years ago
- Calculating FLOPs of Pre-trained Models in NLP☆18Updated 4 years ago
- JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning☆10Updated 10 months ago
- ☆59Updated 2 years ago
- Source code for our AAAI'22 paper 《From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression》☆25Updated 3 years ago
- Pytorch implementation of paper "Efficient Nearest Neighbor Language Models" (EMNLP 2021)☆73Updated 3 years ago
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆98Updated last year