Pinned Repositories
-cluster
客户价值聚类分析
10-steps-to-become-a-data-scientist
📢 Ready to learn! you will learn 10 skills as data scientist:📚 Machine Learning, Deep Learning, Data Cleaning, EDA, Learn Python, Learn python packages such as Numpy, Pandas, Seaborn, Matplotlib, Plotly, Tensorfolw, Theano...., Linear Algebra, Big Data, Analysis Tools and solve some real problems such as predict house prices.
ChatGLM-webui
A WebUI for ChatGLM-6B
cs229t
Statistical Learning Theory (CS229T) Lecture Notes
kxy-python
A toolkit to boost the productivity of machine learning engineers.
pytest
The pytest framework makes it easy to write small tests, yet scales to support complex functional testing
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
pytorch-tutorial
PyTorch Tutorial for Deep Learning Researchers
textflint
Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
Tips-of-Feature-engineering
A feature engineering kit for each issue, to give you a deeper and deeper understanding of the work of feature engineering!
fudp's Repositories
fudp/AIFoundation
AIFoundation 主要是指AI系统遇到大模型，从底层到上层如何系统级地支持大模型训练和推理，全栈的核心技术。
fudp/AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
fudp/awesome-generative-ai-guide
A one stop repository for generative AI research updates, interview resources, notebooks and much more!
fudp/Awesome-LLM-Inference
📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.
fudp/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
fudp/data-juicer
Making data higher-quality, juicier, and more digestible for any large models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！
fudp/garak
the LLM vulnerability scanner
fudp/grok-1
Grok open release
fudp/InternVL
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4V. 接近GPT-4V表现的可商用开源模型
fudp/JusticeFighter110
田柯宇 (Tian Keyu)恶意攻击集群事件的证据揭露
fudp/KwaiAgents
A generalized information-seeking agent system with Large Language Models (LLMs).
fudp/LLaMA-Factory
Unify Efficient Fine-Tuning of 100+ LLMs
fudp/llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
fudp/LLMBox
fudp/LLMs-from-scratch
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
fudp/LLMsNineStoryDemonTower
【LLMs九层妖塔】分享 LLMs在自然语言处理（ChatGLM、Chinese-LLaMA-Alpaca、小羊驼 Vicuna、LLaMA、GPT4ALL等）、信息检索（langchain）、语言合成、语言识别、多模态等领域（Stable Diffusion、MiniGPT-4、VisualGLM-6B、Ziya-Visual等）等 实战与经验。
fudp/minimind-v
「大模型」3小时从0训练27M参数的视觉多模态VLM，个人显卡即可推理训练！
fudp/mlc-llm
Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
fudp/mnn-llm
llm deploy project based mnn.
fudp/ModelCache
A LLM semantic caching system aiming to enhance user experience by reducing response time via cached query-result pairs.
fudp/netron
Visualizer for neural network, deep learning and machine learning models
fudp/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.
fudp/Post-Training-Data-Flywheel
We aim to provide the best references to search, select, and synthesize high-quality and large-quantity data for post-training your LLMs.
fudp/SuperCLUE-Safety
SC-Safety: 中文大模型多轮对抗安全基准
fudp/swarm
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
fudp/TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
fudp/Thinking-Claude
Let your Claude able to think
fudp/tvm-cn
TVM Documentation in Chinese Simplified / TVM 中文文档
fudp/tvm_mlir_learn
compiler learning resources collect.
fudp/UniPortrait
UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization