- nanjing
Stars
Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 40+ benchmarks
Mastering NLP from Foundations to LLMs, Published by Packt
Official implementation of RMoE (Layerwise Recurrent Router for Mixture-of-Experts)
AdalFlow: The “PyTorch” library to auto-optimize any LLM tasks.
A multimodal agent framework for solving complex tasks
GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型
DSPy: The framework for programming—not prompting—foundation models
Distributed Machine Learning Patterns from Manning Publications by Yuan Tang https://bit.ly/2RKv8Zo
Distributed Machine Learning with Python, published by Packt
Notebooks for the O'Reilly book "Learning Ray"
An enterprise-grade AI retriever designed to streamline AI integration into your applications, ensuring cutting-edge accuracy.
Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.
AISystem 主要是指AI系统,包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
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。支持下游任务sft微调,给出三元组信息抽取微调示例。
This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) avai…
Reference implementation for DPO (Direct Preference Optimization)
🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Experts via Clustering
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
Question and Answer based on Anything.
Create LLM agents with long-term memory and custom tools 📚🦙
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Scalable toolkit for efficient model alignment
A research project for natural language generation, containing the official implementations by MSRA NLC team.
A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).