Stars
GraphRAG的应用实例,项目特点在于提供了替换OpenAI模型的方法,并通过修改原有提示和切分文档的方法,提高了GraphRAG处理中文内容的能力。
Fully open reproduction of DeepSeek-R1
DeepSeek r1 and Claude 3.5 Sonnet achieve the best combination, fully unleashing the power of the strongest models. Supports OpenAI streaming output and can run on your favorite ChatBox!
Let your Claude able to think
A modular graph-based Retrieval-Augmented Generation (RAG) system
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)
Retrieval and Retrieval-augmented LLMs
Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo
Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo
MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone
Rocket-recycling with Reinforcement Learning
TOMM2020 Dual-Path Convolutional Image-Text Embedding with Instance Loss 🐾 https://arxiv.org/abs/1711.05535
CNN-RNN中文文本分类,基于TensorFlow
MachineLP / models
Forked from tensorflow/modelsModels and examples built with TensorFlow
Google Research
Facilitating the design, comparison and sharing of deep text matching models.
Python framework to get video analytics / shot boundaries detection / etc..
Models and examples built with TensorFlow
cvpr2024/cvpr2023/cvpr2022/cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集,极市团队整理
Destruction and Construction Learning for Fine-grained Image Recognition
Train the HRNet model on ImageNet
the scott CPU from "But How Do It Know?" by J. Clark Scott
💻📖 Laws, Theories, Principles and Patterns that developers will find useful. #hackerlaws
Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.