Starred repositories
Emotion text classification using Llama3-8b with LoRA and FlashAttention. Based on LLaMA-Factory.
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Instruct-tune LLaMA on consumer hardware
Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
使用rnn,lstm,gru,fasttext,textcnn,dpcnn,rnn-att,lstm-att,兼容huggleface/transformers,以及以transforemrs作为词嵌入模型,后面接入cnn、rnn、attention等等做文本分类。以及各个模型的对比
使用Bert,ERNIE,进行中文文本分类
CNN-RNN中文文本分类,基于TensorFlow
Sentiment Analysis, Text Classification, Text Augmentation, Text Adversarial defense, etc.;
Aspect Based Sentiment Analysis, PyTorch Implementations. 基于方面的情感分析,使用PyTorch实现。
The official implementation of ACL2022``Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks''
互联网仍有记忆!那些曾经在校招过程中毁过口头offer、意向书、三方的公司!纵然人微言轻,也想尽绵薄之力!
[Unofficial] Predict code for AAAI 2022 paper: Unified Named Entity Recognition as Word-Word Relation Classification
基于Tensorflow2.3开发的NER模型,都是CRF范式,包含Bilstm(IDCNN)-CRF、Bert-Bilstm(IDCNN)-CRF、Bert-CRF,可微调预训练模型,可对抗学习,用于命名实体识别,配置后可直接运行。
ACL 2022: BRIO: Bringing Order to Abstractive Summarization
Firefly中文LLaMA-2大模型,支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型
Llama中文社区,Llama3在线体验和微调模型已开放,实时汇总最新Llama3学习资料,已将所有代码更新适配Llama3,构建最好的中文Llama大模型,完全开源可商用
基于torch的,支持logits、crf、span、global_pointer四种方法的命名实体识别任务框架
The GitHub repository for the paper "Informer" accepted by AAAI 2021.