yxk9810 Goto Github PK

2023gaiicfork

afac23

airticketbooking

allennlp

An open-source NLP research library, built on PyTorch.

awesome-php

A curated list of amazingly awesome PHP libraries, resources and shiny things.

baby-llama2-chinese_kaggle

参考https://github.com/DLLXW/baby-llama2-chinese ，从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

backbone

Give your JS App some Backbone with Models, Views, Collections, and Events

bag

Implementation for NAACL-2019 paper

bart_fid

bart_pretrain

bert

TensorFlow code and pre-trained models for BERT

bert-ner-pytorch

Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)

bert-pretrain

不用tensorflow estimator，分别采用字mask和wwm mask在中文领域内finetune bert模型

bert4torch

参考bert4keras的pytorch实现

bert_binary_classification

bert_deep_pretrain

Bert、深度预训练、transformers、pytorch

bert_language_understanding

Pre-training of Deep Bidirectional Transformers for Language Understanding: pre-train TextCNN

bert_text_sim

基于Bert的文本相似度训练框架框架，包含了cross_encoder(Bert A,B句)和bi_encoder(sentenceBert和SimCSE)两种常见的文本相似度

bertclassifier

基于PyTorch的BERT中文文本分类模型（BERT Chinese text classification model implemented by PyTorch）

bloom-lora

Due to restriction of LLaMA, we try to reimplement BLOOM-LoRA (much less restricted BLOOM license here https://huggingface.co/spaces/bigscience/license) using Alpaca-LoRA and Alpaca_data_cleaned.json

ccks23cls

ccks_kg

ccks2020基于本体的金融知识图谱自动化构建技术评测第五名方法总结

chatglm-6b

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

chatglm-6b-qlora

使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。

chatpdf_qwen

chinese-text-classification-pytorch

中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

chinese-tokenization

利用传统方法（N-gram，HMM等）、神经网络方法（CNN，LSTM等）和预训练方法（Bert等）的中文分词任务实现【The word segmentation task is realized by using traditional methods (n-gram, HMM, etc.), neural network methods (CNN, LSTM, etc.) and pre training methods (Bert, etc.)】

chinese-vicuna

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

chinese_ner

一个中文简单的命名实体：有hmm、BiLSTM、BiLSTM-CRF，基于pytorch。

chinesesquad

中文机器阅读理解数据集