Lists (1)
Starred repositories
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。
My solution to the book <A collection of Data Science Take-home Challenges>
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
GRID: Generative Recommendation with Semantic IDs
An implementation of a deep learning recommendation model (DLRM)
[WSDM'2024 Oral] "SSLRec: A Self-Supervised Learning Framework for Recommendation"
Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).
Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.
A configurable, tunable, and reproducible library for CTR prediction https://fuxictr.github.io
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.
[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"
A list of awesome papers and resources of recommender system on large language model (LLM).
Easy-to-use,Modular and Extendible package of deep-learning based CTR models .
A powerful tool for creating fine-tuning datasets for LLM
A self-hosted dashboard that puts all your feeds in one place
An alternative to the immich-CLI command that doesn't depend on nodejs installation. It tries its best for importing google photos takeout archives.
MinIO is a high-performance, S3 compatible object store, open sourced under GNU AGPLv3 license.
A Counter-Strike 2 Demo Parser for Go (demoinfo)
Open Source Continuous File Synchronization
A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.