Agent frameworks & infrastructure

Models, fine-tuning & training

2,504 agents · most starred first

Models, fine-tuning & training, page 23 of 26

gptnl

A placeholder for the codebase of GPT-NL

gptperoz

Train AI in 3 lines - The simplest PyTorch alternative

gptzip

losslessly compress data with language models

gradgpt

Adam who? Your next PyTorch optimiser can be a cutting-edge LLM...

gradient-swarm-optimization

A Python implementation of Gradient-guided Swarm Optimization algorithm

green-bit-llm

A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.

groq-qa-generator

Groq QA automates question-answer generation from text with LLaMA 3 and Hugging Face to fine-tune large language models (LLMs).

heretic-llm

Training-free language model modification

hugo-rl-llm

Open-source framework for Reinforcement Learning integrated with Large Language Models

hypellm

A toolkit for LLM data augmentation

iotagents

iotagents - Pytorch

jam-gpt

A reimplementation of large language model (LLM) architectures designed for research and development processes

jaxagents

JAX implementation of Reinforcement Learning agents

k-llmmeans

k-LLMmeans clustering algorithm

kan-gpt

Awesome kan_gpt created by AdityaNG

keragan

Keras GAN Library

keras-gemini

A Python package that combines the power of Keras with Gemini for natural language-driven neural network building.

keras-gpt

From zero to GPT-hero with Keras 3

keras-gpt-2

GPT-2

kesmarag-toolbox

kesmarag-toolbox

kogpt2-transformers

Transformers library for KoGPT2

kydon-gpt

A PyTorch-based GPT model implementation with configurable architecture

lairgpt

A Pytorch-based package by LightOn AI Research allowing to perform inference with PAGnol models.

langchain-huggingface

An integration package connecting Hugging Face and LangChain.

lazyllm-llamafactory

Easy-to-use LLM fine-tuning framework

lazyllm-verl

An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

lightgpt

LightGPT lightweight GPT

lightning-gpt

GPT training in Lightning

litgpt

Hackable implementation of state-of-the-art open-source LLMs

llama-factory-recorder

Dora Node for VLM

llama-index-finetuning

llama-index finetuning

llama-index-orpo-dpo-dataset-generator

A dataset generator for llama index to aid in generating ORPO & DPO datasets

llama-index-readers-datasets

llama-index readers HuggingFace Datasets integration

llama-index-utils-huggingface

llama-index utils for huggingface integration

llama-models

Llama models

llama-stack-provider-kft

Llama Stack Provider for Distributed InstructLab Training using KFT

llama-trainer

Llama trainer utility

llama2-lora-adapter

LoRA adapter for Llama2

llama3tokenizers

a place downloading llama3tokenizers

llamadatasets-llamasearch

Dataset management and processing library for LlamaSearch.ai applications

llamafactory

Unified Efficient Fine-Tuning of 100+ LLMs

llamafactory-ascend

a fake package to warn user wrong installation

llamafactory-songlab

Easy-to-use LLM fine-tuning framework

llamafarm-forge

Self-improving SLM training platform — autonomous fine-tuning with Claude-powered experiment planning

llamagym

Fine-tune LLM agents with online reinforcement learning

llamascopium

For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research. Open-sourced and constantly updated.

llamatune

Haven's Tuning Library for LLM finetuning

llm-alignment

A small example package

llm-bhasa

LLM trainer

llm-datasets

A collection of datasets for language model training including scripts for downloading, preprocesssing, and sampling.

llm-distil

Knowledge Distillation for Large Language Models

llm-distiller

Model distiller automator — recursively drives an LLM with seed prompts and stores compressed outputs in SQLite

llm-evolution

LLM + evolutionary algorithms to optimize programs in multiple languages and domains

llm-forge-new

Config-driven, YAML-first open-source LLM training platform

llm-foundry

LLM Foundry

llm-magnet

the small distributed language model toolkit. fine-tune state-of-the-art LLMs anywhere, rapidly.

llm-markov

Plugin for LLM adding a Markov chain generating model

llm-refresh-wheel

Keep your local LLM fresh without forgetting what it already knows — replay buffers + forgetting metrics + auto-rollback for continual fine-tuning

llm-rewards

Lean, modular reward functions for RL training with LLMs

llm-ripper

A production framework for modular deconstruction, analysis, and recomposition of knowledge in Transformer-based language models

llm-sc-curator

Dynamic feature distillation framework for robust zero-shot LLM annotation.

llm-scratch-lab

A toolkit for building an LLM from scratch

llm-sepweight

Microlib for converting LLM weights into sepweight format

llm-toolkit

LLM Finetuning resource hub + toolkit

llm-tools-5

LLM Fine Tuning

llm-toys

Small(7B and below), production-ready finetuned LLMs for a diverse set of useful tasks.

llm-trainer

🤖 Train your LLMs with ease and fun.

llm2slm

Convert Large Language Models to Small Language Models with CLI, Web UI, and IDE integration

llm4pcg

LLM4PCG is a python package containing required and utility functions of ChatGPT4PCG competition, but modified to support local LLMs that compatible with OpenAI API interface.

llm_atc

Tools for fine tuning and serving LLMs

llmassist

A easy assist package for Large Language model inference and fine-tuning.

llmbuilder

A comprehensive toolkit for building, training, and deploying language models

llmcollection

Implementation of LLMs in pytorch

llmdata

rubrics

llmdataset

llm dataset

llmize

A library to use Large Language Models (LLMs) as numerical optimizers

llmpy-models

Automatically generated LLM models for llmpy-lib

llmrelic

A lightweight Python library providing easy access to popular LLM model names, metadata (context windows, capabilities, pricing tiers), and support definitions. Born from a failed experiment on context data compression for LLMs with finite context windows, this library helps developers manage model names, validate support, search by capabilities, and find models by requirements without hardcoding strings or maintaining spreadsheets.

llmring-registry

LLMRing public model registry CLI and tools (manual curation workflow)

llmrush

LlmRush: A Python package for training and Inference language models

llms-dev

Fuzzy search LLM models from models.dev

llmtensor
llmtorch

llm model process for pytorch

llmtune

llmtune

llmtuner

Easy-to-use LLM fine-tuning framework

local-llm-finetune

Fine-tune an LLM with Unsloth

londonaicentre-oncollama-assets

OncoLlama assets

londonaicentre-schemallama-types

SchemaLlama types

longdllm

Plug-and-play long context adaptation for diffusion language models

mb-llm

llm tool for the MB project for Fine-tuning and Segmentation

memgpt

This package contains the code for training a memory-augmented GPT model on patient data. Please note that this is not the 'letta' company project with thehttps://github.com/letta-ai/letta; for use of their package, plsuse 'pymemgpt' instead.

meta-llama-3-yarn

YaRN Implementation compatible with HuggingFace Transformers

metaformer-gpt

Metaformer - GPT

mh-llm

A Metropolis-Hastings based sampling framework for LLMs.

mimo-llm

A language model fine-tuned for code and conversation.

minegpt2

from skt AI

minichatgpt

A RLFH implementation (ChatGPT) powered by ColossalAI

minigptai

A lightweight GPT-style transformer for research and inference.

mint-llm

Meaning-Informed Next-token Transformation

mistral-jax

JAX implementation of the Mistral model.

More in Agent frameworks & infrastructure