Pinned Repositories
algorithms
Minimal examples of data structures and algorithms in Python
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.
Bipropagation
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。
Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
chinese-poetry
A dataset under construction of Chinese Poetry 中文古文诗词数据集,，近1,4000诗人, 107,891唐诗，275,581宋词。
Classical-Modern
非常全的文言文（古文）-现代文平行语料
Coloring-t-SNE
Exploration of methods for coloring t-SNE.
DeepLearning_LHY21_Notes
深度学习 李宏毅 2021 学习笔记
fanqiang
翻墙-科学上网
D0z1ngShark's Repositories
D0z1ngShark/algorithms
Minimal examples of data structures and algorithms in Python
D0z1ngShark/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.
D0z1ngShark/Bipropagation
D0z1ngShark/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。
D0z1ngShark/Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
D0z1ngShark/chinese-poetry
A dataset under construction of Chinese Poetry 中文古文诗词数据集,，近1,4000诗人, 107,891唐诗，275,581宋词。
D0z1ngShark/Classical-Modern
非常全的文言文（古文）-现代文平行语料
D0z1ngShark/Coloring-t-SNE
Exploration of methods for coloring t-SNE.
D0z1ngShark/DeepLearning_LHY21_Notes
深度学习 李宏毅 2021 学习笔记
D0z1ngShark/fanqiang
翻墙-科学上网
D0z1ngShark/ML2021-Spring
李宏毅 (Hung-Yi Lee) 機器學習 Machine Learning 2021 Spring
D0z1ngShark/movenet
Google's Next Gen Pose Estimation in PyTorch
D0z1ngShark/fucking-algorithm
刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.
D0z1ngShark/lit-gpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
D0z1ngShark/minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
D0z1ngShark/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
D0z1ngShark/nlp-tutorial
Natural Language Processing Tutorial for Deep Learning Researchers
D0z1ngShark/openbilibili-go-common
🙈！🙉！🙊！我不清楚这些是啥… 想谈道德的请把出门右转996.icu！
D0z1ngShark/phx
9Android 客户端，突破游客每天观看10次视频的限制，还可以下载视频
D0z1ngShark/Prompt-Engineering-Guide
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
D0z1ngShark/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
D0z1ngShark/Simple_LLM_PPO
D0z1ngShark/Skywork
Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，评估方法。
D0z1ngShark/SparkInternals
Notes talking about the design and implementation of Apache Spark
D0z1ngShark/the-algorithm
Source code for Twitter's Recommendation Algorithm
D0z1ngShark/the-algorithm-ml
Source code for Twitter's Recommendation Algorithm
D0z1ngShark/TinyLlama
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
D0z1ngShark/Transformer_Example
D0z1ngShark/weibo_terminater
Final Weibo Crawler Scrap Anything From Weibo, comments, weibo contents, followers, anythings. The Terminator
D0z1ngShark/XgboostAndLR
use xgboost and lr model for text classification. xgboost is used to be a feature transform for LR