赵泽宇's repositories
alignment-handbook
Robust recipes to align language models with human and AI preferences
Awesome-AGI
AGI资料汇总学习(主要包括LLM和AIGC),持续更新......
awesome-DeepLearning
深度学习入门课、资深课、特色课、学术案例、产业实践案例、深度学习知识百科及面试题库The course, case and knowledge of Deep Learning and AI
awesome-RLHF
A curated list of reinforcement learning with human feedback resources (continually updated)
ChatLM-mini-Chinese
中文对话0.2B小模型(ChatLM-Chinese-0.2B),开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调。
Chinese-CLIP
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
CodeGeeX
CodeGeeX: An Open Multilingual Code Generation Model
ColossalAI
Making big AI models cheaper, easier, and scalable
Crosstalk-Generation
Perform crosstalk with Qian Yu
Cxx_HOPL4_zh
Chinese translation of Bjarne Stroustrup's HOPL4 paper
DeepSpeedExamples
Example models using DeepSpeed
flink-recommandSystem-demo
:helicopter::rocket:基于Flink实现的商品实时推荐系统。flink统计商品热度,放入redis缓存,分析日志信息,将画像标签和实时记录放入Hbase。在用户发起推荐请求后,根据用户画像重排序热度榜,并结合协同过滤和标签两个推荐模块为新生成的榜单的每一个产品添加关联产品,最后返回新的用户列表。
flink-simple-tutorial
:bell::pill:flink简易使用教程,结合官方仓库的example样例,结合常见场景,使用flink的基本功能
gold-miner
🥇掘金翻译计划,可能是世界最大最好的英译中技术社区,最懂读者和译者的翻译平台:
gpt_academic
为GPT/GLM提供图形交互界面,特别优化论文阅读润色体验,模块化设计支持自定义快捷按钮&函数插件,支持代码块表格显示,Tex公式双显示,新增Python和C++项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持清华chatglm等本地模型
HGB
Revisiting, benchmarking, and refining Heterogeneous Graph Neural Networks.
JARVIS
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
lightllm
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
LLaMA-Factory
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
LLM-Tuning
Tuning LLMs with no tears💦, sharing LLM-tools with love❤️.
lora
Using Low-rank adaptation to quickly fine-tune diffusion models.
MiniGPT-4
MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models
models
A collection of pre-trained, state-of-the-art models in the ONNX format
MOSS
An open-source tool-augmented conversational language model from Fudan University
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Phi2-mini-Chinese
Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型,支持加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.