Projects sharing features with Self Instruct

This project provides an end-to-end framework for adapting large language models to follow user instructions through supervised fine-tuning. It functions as a comprehensive training pipeline that enables the creation of specialized assistant models by minimizing the difference between predicted outputs and target responses within structured instruction datasets. The framework distinguishes itself by integrating synthetic data generation with memory-efficient training techniques. It utilizes powerful language models to iteratively expand small sets of human-written seeds into diverse, high-qua

This project provides a Chinese large language model based on the LLaMA architecture. It is an instruction-tuned model optimized for natural language processing and multi-turn conversations in Chinese. The system includes a framework for parameter-efficient fine-tuning using low-rank adaptation and quantization to reduce memory requirements. It also implements retrieval augmented generation for local document question answering and supports long-context processing for sequences up to 64K tokens. The project covers a broad set of capabilities including supervised instruction tuning, reinforce

This project is a collection of educational resources and technical guides focused on the development and implementation of large language models. It provides a comprehensive curriculum covering transformer architectures, training methods, and deployment strategies. The materials provide detailed instructions for building autonomous agents using reasoning loops and tool integration, as well as guides for fine-tuning models through supervised learning and preference optimization. It also includes tutorials for constructing retrieval augmented generation pipelines and implementing transformer m

Open-Instruct is a distributed training and instruction tuning framework for large language models. It functions as a coordinator for supervised fine-tuning, reinforcement learning from human feedback pipelines, and tool-use training, providing specialized roles for dataset curation and model alignment. The project distinguishes itself through a high-performance training architecture that utilizes actor-based distributed coordination and hybrid sharding to manage large GPU clusters. It implements advanced alignment techniques including direct preference optimization, group relative policy opt

This project is a training pipeline and framework for developing Chinese language models based on the Llama 2 architecture. It functions as a distributed GPU trainer and dataset preprocessing toolkit designed for both the initial pre-training of baseline models and subsequent supervised fine-tuning. The system distinguishes itself through a specialized workflow for Chinese text, incorporating a data curation pipeline that uses similarity hashing for deduplication and a tokenization process that converts raw text into memory-mapped binary files for efficient disk access. It implements a superv

UltraChat is a collection of large-scale conversational datasets and instruction-tuning data designed for training and evaluating generative AI models. It provides structured JSON data consisting of complex, multi-round dialogue sequences intended to refine the performance of large language models in chat tasks. The project focuses on improving reasoning and response quality through a diverse set of interactions across multiple sectors. These datasets are used for supervised fine-tuning and instruction tuning workflows to improve how models follow complex directions and maintain context acros

PromptWizard is an automated prompt engineering framework designed to evolve natural language instructions for generative tasks. It functions as an in-context learning optimizer and synthetic data generator, using mutation rounds and performance metrics to iteratively refine large language model instructions. The system employs a self-reflective optimization loop that uses model-generated critiques to rewrite prompts. It distinguishes itself through the use of reasoning chain integration and persona-based prompting to steer the tone and professional quality of model responses. The framework

Dolly is an instruction-tuned large language model designed to follow complex natural language directions. It operates as a causal language model that predicts the next token in a sequence to generate coherent conversational responses and perform tasks such as brainstorming, classification, and question answering. The project focuses on the development of models using open datasets suitable for commercial application. It enables the creation of instruction-following models by utilizing curated collections of human-generated instruction-response pairs. The repository provides capabilities for

This project is a comprehensive educational curriculum and engineering handbook focused on the lifecycle of large language models. It serves as a structured knowledge base for machine learning practitioners, covering the fundamental mathematical and architectural principles of transformer-based sequence modeling, as well as the practical implementation of supervised instruction fine-tuning and preference-based model alignment. The repository distinguishes itself by providing a deep dive into advanced model composition and optimization techniques. It details methodologies for weight-space mode

This project is a generative AI educational resource and natural language processing course. It serves as a technical implementation guide for building, pre-training, and fine-tuning a large language model from scratch using PyTorch. The curriculum provides a step-by-step tutorial on large language model development, focusing specifically on the design of transformer-based text generation models. It includes dedicated instruction on parameter-efficient fine-tuning to optimize training by updating only a small subset of model weights. The material covers the end-to-end generative AI training

LMFlow is a comprehensive suite for large language model fine-tuning, context extension, multimodal processing, and inference execution. It provides a toolkit for updating model parameters through full tuning or memory-efficient adapter algorithms, alongside an inference engine for executing tuned models via command-line or web-based interfaces. The framework includes a dedicated alignment suite for supervised tuning and reward model training to refine model behavior. It features a context window extender to increase maximum input lengths and a multimodal framework for building chatbots that

LLM4Decompile is a toolset and framework for binary-to-source code translation. It uses large language models to transform machine code into readable source code and recover the original logic of compiled executables. The project includes a specialized pipeline for generating synthetic training datasets by converting source code into assembly pairs. It provides a fine-tuning framework to optimize deep learning models on these binary-to-source datasets, increasing the accuracy of code recovery. The system also features capabilities for refining decompiled pseudo-code. This process focuses on

Chinese-Vicuna is a Chinese large language model and instruction-following AI based on the LLaMA architecture. It is specifically designed for natural language understanding and generation in the Chinese language, utilizing an instruction-tuned model to follow complex user prompts across conversations. The project provides a LoRA fine-tuning framework and quantization systems to enable model adaptation and inference on consumer hardware. It implements quantized inference to reduce memory usage on both CPUs and GPUs, supported by a low-level C++ implementation to minimize system resource requi

This project is a comprehensive technical course study guide and reference for learning the architectures and training methods of Transformers and large language models. It serves as a technical overview for understanding how neural networks process data and how to align model behavior with specific performance goals. The repository provides specialized guides on several key areas of model development. This includes detailed references for transformer architectures, implementation frameworks for retrieval-augmented generation and agentic workflows, and technical guides for model optimization

This project is a comprehensive toolkit for adapting large language models to the Chinese language, providing a specialized framework for fine-tuning, inference, and local deployment. It serves as a coordinated suite for language-specific adaptation, including tools for expanding tokenizers and implementing retrieval-augmented generation. The project distinguishes itself through a complete pipeline for model adaptation, featuring multilingual tokenizer expansion and a fine-tuning framework that supports instruction-based supervised training and adapter merging. It also includes a dedicated de

Huatuo-Llama-Med-Chinese is a medical large language model specialized in processing and generating natural language text in Chinese. It is an instruction-tuned system designed to answer professional healthcare questions by leveraging a dedicated medical knowledge base. The model integrates structured medical literature and knowledge graphs to ensure clinical accuracy during response generation. It employs knowledge-graph augmented inference to combine structured entity relationships with neural network outputs. The system is developed through domain-specific weight adaptation, cross-lingual

This project provides a foundational framework and reference implementation for executing causal language modeling and multimodal reasoning on local systems. It includes a set of core components for managing model assets, a fine-tuning framework, and structural definitions required to instantiate transformer-based architectures. The system is distinguished by its ability to process combined text and image inputs through multimodal transformer models for visual reasoning and document analysis. It also supports the deployment of quantized models, reducing memory footprints through low-precision

This project is an educational program focused on the alignment of small language models. It provides a technical curriculum and a series of courses designed to teach how to align models with human preferences and behaviors. The material covers the implementation of preference optimization algorithms and the adaptation of vision-language models to process both text and image data simultaneously. It also includes instructional guides on synthetic data generation to improve model performance in specialized domains. The curriculum encompasses supervised fine-tuning workflows, the use of chat te

This project is a fine-tuning framework and training pipeline designed to optimize and adapt large language and vision models. It provides a specialized toolkit for parameter-efficient tuning and supervised learning, serving as both a trainer for multimodal models and a deployment tool for serving fine-tuned models via high-performance inference engines. The framework focuses on reducing memory and compute requirements by updating a small subset of model parameters. It supports a wide range of adaptation strategies, including vision-language model training to align text, image, video, and aud

CodeLlama is a family of large language models derived from the Llama 2 architecture and specialized for producing, completing, and refactoring source code across multiple programming languages. It functions as a code generation model capable of synthesizing source code from natural language descriptions. The project includes specific model variants designed for different programming tasks. This includes instruction-tuned models trained to follow complex natural language directions and code infilling models that predict and insert missing code segments into existing files by analyzing surroun

Code Llama is a large language model based on Llama 2 trained specifically for programming tasks and software development. It provides specialized model types optimized for general code generation, instruction following, and context-aware infilling. The project includes an instruction-tuned programming model for executing technical tasks via natural language prompts and a code infilling model that predicts missing sections based on surrounding source context. A large context code model is also provided to analyze extensive blocks of source code for improved coherence. The system covers capab

This project is a comprehensive educational curriculum and structured learning path covering the full lifecycle of large language models. It provides a guided progression through the theory, architecture, training, and deployment of these models. The curriculum includes specialized guides on transformer architecture, model training tutorials, and frameworks for designing autonomous agents. It also provides dedicated resources for studying model safety and ethics. The material covers a wide range of technical capabilities, including distributed training strategies, parameter-efficient fine-tu

This is the repo for the Code Alpaca project, which aims to build and share an instruction-following LLaMA model for code generation. This repo is fully based on Stanford Alpaca ,and only changes the data used for training. Training approach is the same.

This repository contains the Unnatural Instructions dataset. Unnatural Instructions is a dataset of instructions automatically generated by a Large Language model. See full details in the paper: "Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor"

Let ChatGPT teach your own chatbot in hours with a single GPU!

Dromedary: towards helpful, ethical and reliable LLMs.