Projects sharing features with So Large Lm

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

Nexent is an enterprise AI control plane and LLM agent orchestration platform. It provides a zero-code environment for designing, deploying, and managing production AI agents through a multi-agent collaboration framework that coordinates specialized autonomous agents using standardized messaging protocols. The platform integrates the Model Context Protocol to connect agents with external tools, plugins, and services via a universal communication interface. It further distinguishes itself with a dedicated RAG knowledge base manager that imports unstructured documents and utilizes hybrid search

This project is a comprehensive framework for building, evaluating, and connecting autonomous agent systems. It provides a library of standardized architectural patterns for implementing complex agent workflows, including multi-agent orchestration, iterative reasoning, and memory management. By offering a unified interface for model providers, the framework allows for consistent agent execution across different artificial intelligence services. The framework distinguishes itself through a focus on rigorous benchmarking and deterministic control. It includes a suite of tools for evaluating age

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

This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex

This project is an educational resource and software architecture framework focused on the technical foundations of large language model engineering. It provides a collection of guides and design patterns for building and maintaining professional, scalable systems using large language models. The resource outlines practical implementation patterns for orchestrating workflows that combine prompt engineering, model calls, and vector databases. It focuses on transforming prompt development into a structured engineering process to ensure reliable model outputs in production environments. The cov

Tiny Universe is an educational monorepo that delivers multiple independent implementations of core AI subsystems as self-contained Jupyter notebooks. It provides from-scratch constructions of foundational architectures including a complete Transformer model built from the original paper specification, a denoising diffusion probabilistic model for image generation, and a ReAct-style autonomous agent framework that equips an LLM with tools for planning and multi-step task execution. The project distinguishes itself by covering the full lifecycle of modern AI systems through hands-on implementa

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a configurable training pipeline orchestrated through YAML recipes, with CLI overrides and component swapping, distributed training via FSDP2, memory optimizations, and parameter-efficient fine-tuning methods like LoRA, DoRA, and QLoRA. The library distinguishes itself through its YAML-driven configuration system that defines all training parameters and instantiates components from config files, with full CLI override capability for any field or component at launch time. It suppo

This repository is a collection of guides, notebooks, and recipes for implementing advanced prompting techniques and workflow patterns with large language models. It serves as a prompt engineering guide, an evaluation suite for scoring prompt quality, and a framework for orchestrating agents and integrating external tools. The project provides implementation patterns for building applications with Claude, specifically focusing on coordinating multiple models to split complex tasks between high-reasoning and high-efficiency agents. It includes technical demonstrations for multimodal data proce

This project is a collection of scripts and workflows for training, fine-tuning, and deploying large language models using the Hugging Face Transformers toolkit. It functions as a distributed training framework, a library for natural language processing task implementations, and a system for building retrieval-augmented generation chatbots. The repository includes specialized tools for model optimization, such as a Bayesian hyperparameter optimizer for automatically tuning model settings. It provides implementations for scaling model training across multiple graphics processors using data par

Julep is an LLM agent orchestration platform and multi-tenant AI backend designed for building autonomous agents with persistent memory, tool integration, and complex multi-step workflows. It serves as a framework for configuring agent identities and behavioral settings to automate specialized professional roles. The platform distinguishes itself through its stateful session management and RAG infrastructure engine, which allow agents to maintain long-term interaction history and ground responses in indexed private documents. It provides enterprise-grade infrastructure features, including a s

ChatGLM-Efficient-Tuning is a fine-tuning framework and toolkit designed to optimize large language models using parameter-efficient fine-tuning techniques. It provides a pipeline for adjusting model behavior and reducing the memory and compute requirements necessary for training. The project features a web-based trainer and orchestration interface for configuring and executing the fine-tuning process on a single GPU. It supports quantized training in lower precision formats to enable fine-tuning on hardware with limited memory, as well as reinforcement learning from human feedback for model

This project is a transformer-based language model and autoregressive text generator designed to predict the next token in a sequence to produce human-like prose and synthetic text. It functions as a large language model that utilizes a transformer architecture to learn linguistic patterns from large datasets for unsupervised multitask learning. The repository provides a distribution of pre-trained weights, enabling natural language processing tasks without requiring additional training. This allows the model to perform zero-shot task generalization by applying learned patterns to new tasks.

Axolotl is a configuration-driven framework designed for the fine-tuning, evaluation, and quantization of large language models. It functions as a comprehensive orchestrator for distributed training, enabling users to manage complex workflows across multi-node and multi-GPU environments. By utilizing structured configuration files, the platform streamlines the setup of training parameters, dataset paths, and hardware distribution strategies. The project distinguishes itself through its support for diverse training methodologies, including full-parameter tuning, parameter-efficient adaptation,

This project is an educational curriculum and architectural framework for building autonomous AI agents and multi-agent systems. It provides a structured learning path focused on the development of independent software components capable of planning, executing tasks, and utilizing external tools to achieve high-level goals. The framework emphasizes multi-agent system orchestration through distributed architectures where specialized agents collaborate using standardized communication protocols. It details specific design patterns such as dual-memory systems for maintaining short-term plans and

SmolLM is a project dedicated to the development of small language models. It focuses on training and fine-tuning compact models that maintain high performance while utilizing fewer parameters. The project emphasizes efficient AI inference and on-device text generation, aiming to enable the deployment of lightweight models on edge devices with limited memory and processing power. It utilizes synthetic data generation to produce artificial datasets that improve the reasoning and training of these AI systems. The system supports a variety of optimization and training capabilities, including we

This project is a manual reconstruction of the Llama 3 transformer architecture implemented as a PyTorch neural network. It serves as a reference for the internal mathematical structure and tensor flow of a transformer-based language model designed for next token prediction. The implementation focuses on building the model from scratch using basic matrix operations and tensor manipulations. It demonstrates the manual construction of core components, including rotary positional embeddings, multi-head self-attention, and root mean square normalization. The codebase covers the full inference pi

Granite Code Models is a family of transformer-based foundational models designed for software engineering and logical reasoning tasks. These models are trained on high-quality programming datasets to interpret natural language prompts and generate functional source code, explain complex logic, repair code defects, and produce technical documentation. The project distinguishes itself through specialized training methodologies that align model behavior with complex programming instructions and mathematical problem-solving. By utilizing chain-of-thought reasoning and instruction-tuned parameter

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a config-driven system for instantiating components, orchestrating distributed training, and managing parameter-efficient fine-tuning with quantization support, all through YAML-based configurations and command-line overrides. The library distinguishes itself through its comprehensive post-training workflow orchestration, combining supervised fine-tuning, preference optimization (DPO, PPO, GRPO), knowledge distillation, and quantization-aware training in a single configurable pip

Qwen2.5 is a suite of large language model foundation models designed for natural language generation, code production, and complex mathematical reasoning. The project encompasses a multilingual language model capable of processing dozens of languages and a specialized code generation model for technical problem solving and debugging. The framework is distinguished by its long context capabilities, enabling the analysis of massive inputs ranging from 256K up to 1 million tokens. It further functions as an agentic framework, utilizing standardized templates and parsers to execute autonomous wo

FlagAI is a distributed deep learning framework and platform designed for the end-to-end lifecycle of large-scale foundation models. It provides a toolkit for training, fine-tuning, and deploying large language models and multi-modal systems across multi-node computing clusters. The project features hardware-agnostic compute abstractions to ensure consistent execution across different accelerators. It includes a dedicated library for parameter-efficient fine-tuning, allowing large neural networks to be adapted to specific tasks with minimal parameter updates and reduced computational overhead

LLaMA-Adapter is a parameter-efficient fine-tuning framework designed to adapt large language models using a minimal set of trainable parameters. It functions as an instruction tuning tool and a multimodal adapter, allowing pre-trained models to follow human instructions and process non-textual data. The project specializes in the integration of image, video, audio, and sensor data into language models for cross-modal understanding. It enables the customization of LLaMA models through the use of lightweight adapters, which allows for the extraction and storage of learned weights independently

OpenRLHF is a training framework and alignment library designed for reinforcement learning from human feedback across distributed GPU clusters. It provides tools for aligning large language models and multimodal vision-language models using algorithms such as PPO, GRPO, and DPO. The framework distinguishes itself through a distributed inference engine that overlaps sample rollout with training to increase throughput. It supports scaling to models exceeding 70 billion parameters via parameter sharding and handles long-context sequences through ring-attention sequence parallelism. The project

This project is a PyTorch implementation of an attention-based neural network designed for sequence-to-sequence deep learning tasks. It serves as a library for constructing deep learning sequence models that utilize encoder and decoder structures to process natural language and sequential data. The implementation centers on a multi-head attention mechanism to capture diverse relationships between tokens without using recurrence. It includes sinusoidal positional encoding to maintain sequence order and point-wise feed-forward networks to transform token positions independently. The architectu

Swift is a toolkit for the full-parameter and parameter-efficient fine-tuning of large language and multimodal models. It functions as a multimodal model trainer for text, image, video, and audio data, and includes specialized tools for model compression and reinforcement learning from human feedback. The framework provides an alignment toolkit for optimizing model behavior using preference learning algorithms and reinforcement learning. It integrates parameter-efficient fine-tuning methods to adapt models with minimal memory and compute requirements, alongside utilities for reducing hardware

GPT2-Chinese is a Chinese language model implementation based on the GPT-2 architecture. It provides a causal language model trainer and a natural language generation tool designed for training and generating human-like Chinese text sequences. The system integrates a BERT tokenizer to process Chinese corpora into manageable units for machine learning. It enables the development of predictive text models that can generate specific patterns, such as news or poetry, through prompt-based text completion. The project covers a full workflow including text tokenization, model training using a trans