wang-benqiang

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

ChatGLM2-6B

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

GPTQ-for-LLaMa

4 bits quantization of LLaMA using GPTQ

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Chinese-text-correction-papers

text correction papers

TaskMatrix

optimate

A collection of libraries to optimise AI model performances

zero_nlp

中文nlp解决方案(大模型、数据、模型、训练、推理)

PromptCLUE

PromptCLUE, 全中文任务支持零样本学习模型

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Sequence-to-Action

Grammar correct project based Tencent's paper(Sequence to Action)

awesome-chatgpt

Selected ChatGPT demos, tools, articles, and more ✨

CCL2022_CGED-8_Top1_project

CCL2022汉语学习者文本纠错评测任务赛道二——CGED-8第一名解决方案

Fengshenbang-LM

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

GLM-130B

GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

textual_inversion

Chinese-CLIP

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

chinese_clip

中文CLIP：自定义数据集，可根据文图提取向量，实现文图匹配。

ssc

基于“音形码”的中文字符串相似度计算方法

Chinese-Word-Ordering-Errors-Detection-and-Correction-Corpus

Word Ordering Errors (WOEs) are the most frequent type of grammatical errors at sentence level for non-native Chinese language learners. Learners taking Chinese as a foreign language often place character(s) in the wrong places in sentences, and that results in wrong word(s) or ungrammatical sentences. Besides, there are no clear word boundaries in Chinese sentences.

allennlp

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

clean-text

🧹 Python package for text cleaning

flair

A very simple framework for state-of-the-art Natural Language Processing (NLP)

BERTopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

EssayTopicPredictV2

高考作文题目预测模型 v1.0

ERNIE-Pytorch

ERNIE Pytorch Version

google-landmark

Dataset with 5 million images depicting human-made and natural landmarks spanning 200 thousand classes.

Introduced

响应式极简个人简介/介绍页