mathlf2015

ChatTTS

A generative speech model for daily dialogue.

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

llama3

The official Meta Llama 3 GitHub site

pykan

Kolmogorov Arnold Networks

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

yolov10

YOLOv10: Real-Time End-to-End Object Detection

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

trader

交易模块

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

HunyuanDiT

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

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.

Algorithm-Practice-in-Industry

搜索、推荐、广告、用增等工业界实践文章收集（来源：知乎、Datafuntalk、技术公众号）

EasyRec

A framework for large scale recommendation algorithms.

RecSysPapers

推荐/广告/搜索领域工业界经典以及最前沿论文集合。A collection of industry classics and cutting-edge papers in the field of recommendation/advertising/search.

NeuRec

Next RecSys Library

llama3.np

llama3.np is a pure NumPy implementation for Llama 3 model.

wtpy

wtpy是基于wondertrader为底层的针对python的子框架

AutoCoder

We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.

UniTS

A unified multi-task time series model.

papers.cool

Cool Papers - Immersive Paper Discovery

Awesome-Multi-Task-Learning

An up-to-date list of works on Multi-Task Learning

BLACK_NEWS

北京邮电大学郑凤事件完整pdf

gua-area

famous PDF

awesome-chinese-llm

Awesome Chinese LLM: A curated list of Chinese Large Language Model 中文大语言模型数据集和模型资料汇总

paper-reading-note

和李沐一起读论文

Qwen-SFT

阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理

frnet

The Source Code of FRNet

STEM

[AAAI 2024] The open source code for "STEM: Unleashing the Power of Embeddings for Multi-Task Recommendation".

Understanding-the-Ranking-Loss