airaria / TextPruner
A PyTorch-based model pruning toolkit for pre-trained language models
☆370Updated last year
Related projects ⓘ
Alternatives and complementary repositories for TextPruner
- A framework for cleaning Chinese dialog data☆260Updated 3 years ago
- PromptBERT: Improving BERT Sentence Embeddings with Prompts☆332Updated 11 months ago
- Code used for sourcing and cleaning the BigScience ROOTS corpus☆305Updated last year
- ☆273Updated 6 months ago
- text embedding☆138Updated last year
- ☆297Updated last year
- sentence-transformers to onnx 让sbert模型推理效率更快☆162Updated 2 years ago
- The code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task —— Next Sentence Prediction"☆224Updated 2 years ago
- 比Sentence-BERT更有效的句向量方案☆358Updated 2 years ago
- Codebase for RetroMAE and beyond.☆237Updated 5 months ago
- Python ROUGE Score Implementation for Chinese Language Task (official rouge score)☆82Updated 4 months ago
- 中文 Instruction tuning datasets☆118Updated 7 months ago
- A wide variety of research projects developed by the SpokenNLP team of Speech Lab, Alibaba Group.☆107Updated 9 months ago
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆207Updated 11 months ago
- Pytorch version of BERT-whitening☆310Updated 3 years ago
- NLU & NLG (zero-shot) depend on mengzi-t5-base-mt pretrained model☆75Updated 2 years ago
- T2Ranking: A large-scale Chinese benchmark for passage ranking.☆150Updated last year
- Mengzi Pretrained Models☆534Updated last year
- A PyTorch-based toolkit for natural language processing☆153Updated last year
- CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation☆481Updated last year
- Universal information extraction with instruction learning☆371Updated 10 months ago
- A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.☆923Updated 2 years ago
- PERT: Pre-training BERT with Permuted Language Model☆355Updated last year
- 💡GENIUS – generating text using sketches! A strong text generation & data augmentation tool.☆174Updated last year
- 语言模型中文认知能力分析☆235Updated last year
- pCLUE: 1000000+多任务提示学习数据集☆467Updated 2 years ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆69Updated last year
- LERT: A Linguistically-motivated Pre-trained Language Model(语言学信息增强的预训练模型LERT)☆200Updated last year
- 使用sentencepiece中BPE训练中文词表,并在transformers中进行使用。☆109Updated last year
- A curated list of research papers in Sentence Reprsentation Learning and a sts leaderboard of sentence embeddings.☆301Updated last year