nlper's repositories
dstc11-simmc2.1-scut-bds-lab
The code and model parameter files for DSTC-11 simmc2.1 from scut-bds-lab
acl-style-files
Official style files for papers submitted to venues of the Association for Computational Linguistics
Baichuan2
A series of large language models developed by Baichuan Intelligent Technology
ChatGLM2-6B
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
chatgpt-comparison-detection
Human ChatGPT Comparison Corpus (HC3), Detectors, and more! 🔥
chatgpt-web-1
用 Express 和 Vue3 搭建的 ChatGPT 演示网页
Firefly
Firefly(流萤): 中文对话式大语言模型
InternLM
InternLM has open-sourced a 7 billion parameter base model, a chat model tailored for practical scenarios and the training system.
langchain-ChatGLM
langchain-ChatGLM, local knowledge based ChatGLM with langchain ｜ 基于本地知识库的 ChatGLM 问答
LiveChat
Code and Dataset for the paper "LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live Streaming" ACL 2023
LLaMA-Efficient-Tuning
Fine-tuning LLaMA with PEFT (PT+SFT+RLHF with QLoRA)
LLM-Tuning
Tuning LLMs with no tears💦, sharing LLM-tools with love❤️.
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现包括二次预训练、有监督微调、奖励建模、强化学习训练。
qlora
QLoRA: Efficient Finetuning of Quantized LLMs
RoleLLM-public
RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
S-LoRA
S-LoRA: Serving Thousands of Concurrent LoRA Adapters
smile
SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Support
StyleCLIP
Official Implementation for "StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery" (ICCV 2021 Oral)
TigerBot
TigerBot: A multi-language multi-task LLM
VisualGLM-6B
Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型
WebGLM
WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)
XrayGLM
🩺 首个会看胸部X光片的中文多模态医学大模型 | The first Chinese Medical Multimodal Model that Chest Radiographs Summarization.
Zhongjing
A Chinese medical ChatGPT based on LLaMa, training from large-scale pretrain corpus and multi-turn dialogue dataset.