Resources

Large Language Models (LLMs)

• Chinese-LLaMA-Alpaca-3. Chinese LLaMA-3 series LLMs. Star

• Chinese-Mixtral. Chinese Mixtral MoE LLMs. Star

• Chinese-LLaMA-Alpaca-2. Chinese LLaMA-2 and Alpaca-2 LLMs. arXiv 2023. Star

• Chinese-LLaMA-Alpaca. Chinese LLaMA and Alpaca LLMs. arXiv 2023. Star

• VisualCLA. Visual Chinese LLaMA and Alpaca LLMs. Star

Pre-Trained Language Models (PLMs)

• VLE. A multimodal Vision-Language Encoder. Star

• LERT. Pre-trained Chinese LERT. arXiv 2022. Star

• MiniRBT. Pre-trained small models: MiniRBT. arXiv 2023. Star

• PERT. Pre-trained Chinese and English PERT. arXiv 2022. Star

• CINO. Pre-trained Language Model for Chinese Minority. arXiv 2022. Star

• MacBERT. Pre-trained Chinese MacBERT. IEEE/ACM TASLP. Star

• CharBERT. Character-aware pre-trained language model. COLING 2020. Star

• Chinese-ELECTRA. Pre-trained Chinese ELECTRA-large, ELECTRA-base, etc. IEEE/ACM TASLP. Star

• Chinese-XLNet. Pre-trained Chinese XLNet-mid, XLNet-base. arXiv. Star

• Chinese-BERT-wwm. Pre-trained Chinese BERT-wwm, RoBERTa-wwm-ext, RBT3, etc. IEEE/ACM TASLP. Star

Datasets

• ExpMRC. Explainability Evaluation for MRC. Heliyon. Star

• AdvRACE. A dataset for testing robustness of MRC models. Findings of ACL 2021. Star

• CMRC 2019. A sentence cloze dataset for Chinese MRC. COLING 2020. Star

• CJRC. A dataset for Chinese judicial MRC. CCL 2019. Star

• CMRC 2018. A span-extraction dataset for Chinese MRC. EMNLP 2019. Star

• CMRC 2017. A cloze-style Chinese reading comprehension dataset. LREC 2018. Star

• PD & CFT. A Chinese cloze-style MRC dataset: PD&CFT. COLING 2016. Star

Toolkits

• TextPruner. An open-source model pruning toolkit for NLP. ACL 2022 Demo. Star

• TextBrewer. An open-source knowledge distillation toolkit for NLP. ACL 2020 Demo. Star

Models

• RecAdam. An optimizer for fine-tuning PLMs with less forgetting. EMNLP 2020. Star

• PR-Embedding. Conversational word embeddings for retrieval-based dialog system. ACL 2020. Star

• Dual BERT. A neural cross-lingual approach for MRC. EMNLP 2019. Star

• TripleNet. A network for multi-turn for retrieval-based dialog system. CoNLL 2019. Star

Miscs

• ChatGPT-in-Academia. Policies of publishers and conferences towards the using of LLM. Star

• Chinese ACL2020 Blogs. Chinese version of ACL 2020 PC blogs. Star

• LAMB Optimizer (TF). LAMB optimizer for large batch training (TensorFlow version). Star

• NLP Review Scorer. Get a score for the review of your NLP paper. Star

• Chinese MRC Datasets. Collections of Chinese reading comprehension datasets. Star