Pinned Repositories
Baichuan-Chat-Tuning
实现了Baichuan-Chat微调，Lora、QLora等各种微调方式，一键运行。
baichuan-speedup
纯c++的全平台llm加速库，支持python调用，支持baichuan, glm, llama, moss基座，手机端流畅运行chatglm-6B级模型单卡可达10000+token / s，
Baichuan2-Explained
Baichuan2代码的逐行解析版本，适合小白
ChatGLM-Efficient-Tuning-Explained
ChatGLM2-6B-Explained
ChatGLM2-6B-Explained
LLaMA-Factory-Explained
LLaMA-Factory that can fine tune more than 100 model! this is an Chinese code explanation of this model.
llama3_explained
the newest version of llama3，source code explained line by line using Chinese
Qwen-Explained
千问14B和7B的逐行解释
Qwen-Tuning
Qwen-Efficient-Tuning
transformers-Explained
官方transformers源码解析。AI大模型时代，pytorch、transformer是新操作系统，其他都是运行在其上面的软件。
ArtificialZeng's Repositories
ArtificialZeng/Baichuan2-Explained
Baichuan2代码的逐行解析版本，适合小白
ArtificialZeng/Baichuan-Chat-Tuning
实现了Baichuan-Chat微调，Lora、QLora等各种微调方式，一键运行。
ArtificialZeng/Qwen-Explained
千问14B和7B的逐行解释
ArtificialZeng/baichuan-speedup
纯c++的全平台llm加速库，支持python调用，支持baichuan, glm, llama, moss基座，手机端流畅运行chatglm-6B级模型单卡可达10000+token / s，
ArtificialZeng/Qwen-Tuning
Qwen-Efficient-Tuning
ArtificialZeng/llama3_explained
the newest version of llama3，source code explained line by line using Chinese
ArtificialZeng/transformers-Explained
官方transformers源码解析。AI大模型时代，pytorch、transformer是新操作系统，其他都是运行在其上面的软件。
ArtificialZeng/Baichuan-Qwen-Llama-tuning-Explained
Baichuan-Qwen-Llama-tuning-Explained
ArtificialZeng/LLaMA-Factory-Explained
LLaMA-Factory that can fine tune more than 100 model! this is an Chinese code explanation of this model.
ArtificialZeng/fastllm-explained
fastllm-explained
ArtificialZeng/Baichuan2
A series of large language models developed by Baichuan Intelligent Technology
ArtificialZeng/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
ArtificialZeng/Training-Data-Synthesis
[ICLR 2024] Real-Fake: Effective Training Data Synthesis Through Distribution Matching
ArtificialZeng/auto-coder
ArtificialZeng/Awesome-Prompt-Engineering
This repository contains a hand-curated resources for Prompt Engineering with a focus on Generative Pre-trained Transformer (GPT), ChatGPT, PaLM etc
ArtificialZeng/baby-llama2-chinese
用于从头预训练+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.
ArtificialZeng/bitsandbytes
8-bit CUDA functions for PyTorch
ArtificialZeng/Chat-Haruhi-Suzumiya
Chat凉宫春日, 由李鲁鲁, 冷子昂等同学开发的模仿二次元对话的聊天机器人。
ArtificialZeng/CPLLM
ArtificialZeng/fastllm
纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行
ArtificialZeng/Firefly
Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA)，支持微调Llma2、Llama、Baichuan、InternLM、Ziya、Bloom等大模型
ArtificialZeng/GraphCare
[ICLR'24] Enhancing Healthcare Predictions with Personalized Knowledge Graphs
ArtificialZeng/HCL
Hypergraph Contrastive Learning for EHR
ArtificialZeng/ICD_promptLearning
ArtificialZeng/OpenBuddy
Open Multilingual Chatbot for Everyone
ArtificialZeng/parameter-efficient-moe
ArtificialZeng/ProG
All in One: Multi-task Prompting for Graph Neural Networks, KDD 2023.
ArtificialZeng/records-research
ArtificialZeng/seminar
ArtificialZeng/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs