Yanweihong's Stars
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
3b1b/videos
Code for the manim-generated scenes used in 3blue1brown videos
hpcaitech/Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
xai-org/grok-1
Grok open release
Loyalsoldier/v2ray-rules-dat
🦄 🎃 👻 V2Ray 路由规则文件加强版,可代替 V2Ray 官方 geoip.dat 和 geosite.dat,兼容 Shadowsocks-windows、Xray-core、Trojan-Go、leaf 和 hysteria。Enhanced edition of V2Ray rules dat files, compatible with Xray-core, Shadowsocks-windows, Trojan-Go, leaf and hysteria.
jiahe7ay/MINI_LLM
This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.
NVIDIA/Megatron-LM
Ongoing research training transformer models at scale
Stability-AI/generative-models
Generative Models by Stability AI
thu-coai/Safety-Prompts
Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts,用于评估和提升大模型的安全性。
X-PLUG/CValues
面向中文大模型价值观的评估与对齐研究
RVC-Boss/GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
afatcoder/LeetcodeTop
汇总各大互联网公司容易考察的高频leetcode题🔥
charent/Phi2-mini-Chinese
Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型,支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.
01-ai/Yi
A series of large language models trained from scratch by developers @01-ai
leptonai/search_with_lepton
Building a quick conversation-based search demo with Lepton AI.
THUDM/ChatGLM3
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
yichen0831/opencc-python
OpenCC made with Python
AkariAsai/self-rag
This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.
wangschang/web3.0
web3.0知识整理 web3.0知识 web3.0学习资料
openai/openai-cookbook
Examples and guides for using the OpenAI API
xrayfree/free-ssr-ss-v2ray-vpn-clash
长期免费维护数个SSR/SS/V2RAY/VPN/CLASH订阅高速节点链接!电报群:https://t.me/xrayfree
Pawdroid/Free-servers
🚀 免费订阅地址,🚀 免费节点,🚀 6小时更新一次,共享节点,节点质量高可用,完全免费。免费clash订阅地址,免费翻墙、免费科学上网、免费梯子、免费ss/v2ray/trojan节点、谷歌商店、翻墙梯子。注意:目前进入官网需开启代理。
fanmingming/live
✯ 一个可直连访问的电视/广播图标库与相关工具项目 ✯ 🔕 永久免费 直连访问 完整开源 不断完善的台标 支持IPv4/IPv6双栈访问 🔕
FlagOpen/FlagEmbedding
Retrieval and Retrieval-augmented LLMs
liguodongiot/llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
ekzhu/datasketch
MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW
baichuan-inc/Baichuan2
A series of large language models developed by Baichuan Intelligent Technology
BlinkDL/RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
microsoft/DeepSpeedExamples
Example models using DeepSpeed
opendilab/PPOxFamily
PPO x Family DRL Tutorial Course(决策智能入门级公开课:8节课帮你盘清算法理论,理顺代码逻辑,玩转决策AI应用实践 )