Agent frameworks & infrastructure

Models, fine-tuning & training

2,504 agents · most starred first

Models, fine-tuning & training, page 24 of 26

mistral-sae

Sparse AutoEncoder to decode Mistral LLM

mistral-v0.2-jax

JAX implementation of the Mistral v0.2 base model.

ml-agents-reasoning

ML Agents Reasoning Research Platform

ml-model-storage
mllm

Multimodal Large Language Models

mlp-gpt-jax

MLP GPT - Jax

mlswarm

This package trains neural networks using swarm-like optimization algorithms

mmgpt

An open-source framework for multi-modality instruction fine-tuning

model-garage

Open the hood on neural networks. Component-level model surgery, analysis, and composition.

modelaverage

tf-keras, make the average of model weight in same models

modelgpt

LLM-powered AutoML — model selection, tuning, and training via any LLM

modellm

A minimalist LLM modeling library

mojogpt

GPT development tools for Mojo

momma-dragonn

deep learning model training and tracking framework

multiagent-rl-rm

Multi-Agent RLRM Framework

multiagenttrainer

Collect data from multiple sources and run autonomous LLM training via autoresearch

myanmar-gpt

a framework for using myanmar languages models

mypy-boto3-bedrock

Type annotations for boto3 Bedrock 1.44.0 service generated with mypy-boto3-builder 8.12.0

mypy-boto3-bedrock-agentcore-control

Type annotations for boto3 BedrockAgentCoreControl 1.44.7 service generated with mypy-boto3-builder 8.12.0

mypy-boto3-bedrock-data-automation

Type annotations for boto3 DataAutomationforBedrock 1.44.0 service generated with mypy-boto3-builder 8.12.0

mypy-boto3-bedrock-data-automation-runtime

Type annotations for boto3 RuntimeforBedrockDataAutomation 1.44.0 service generated with mypy-boto3-builder 8.12.0

mypy-boto3-bedrock-runtime

Type annotations for boto3 BedrockRuntime 1.44.0 service generated with mypy-boto3-builder 8.12.0

nGPT-pytorch

nGPT

nano-askllm

Unofficial implementation of the Ask-LLM paper 'How to Train Data-Efficient LLMs', arXiv:2402.09668.

nano-gpt

A GPT-2 reproduction following karpathy's nanoGPT youtube videos

nested-ragged-tensors

Utilities for efficiently working with, saving, and loading, collections of connected nested ragged tensors in PyTorch

nn-gpt

LLM-Based Neural Network Generator

nope-gpt

A GPT-style large language model (LLM) with no positional embeddings (NoPE).

oat-llm

Online AlignmenT (OAT) for LLMs.

ollama-forge

Create, retrain, ablate, and convert models for local Ollama

one-line-llm-tuner

A Large Language Model Fine-tuning package. The package uses a single line to fine-tune an LLM by taking care of all the boilerplate in the backend.

oneNeuron-pypi.py-chittariraghu

its an implementation of perceptron

onebitllms

Onebit LLMs

open-agentinstruct

A library for generating instruction-following data using agent-based workflows.

open-gpts

An open-source implementation of large-scale language model (LLM).

openai-finetune

Python client library for the OpenAI Fine-tuning API

openai-finetuner

Default template for PDM package

openai-harmony

OpenAI's response format for its open-weight model series gpt-oss

openenv-agent

Agent client for OpenEnv environments - connects RL agents to OpenEnv servers for inference and training

openllm-func-call-synthesizer

A tool for generating synthetic function call datasets for Large Language Models (LLMs).

original-llm

Minimal decoder-only LLM experiments trained from scratch with PyTorch.

paragrid

Simple parallelized grid search to find the best hyperparameters

parallel-llm

Ultra-fast parallel training and inference for language models

parrotprediction-openai-envs

Custom environments for OpenAI Gym

picogpt

A tiny GPT with tiktoken BPE and RoPE (auto-extend), CUDA/MPS/CPU aware.

pqagent

A user friendly package for training quality prediction models

project-llm-model

LLM and VLM model

project-llm-trainer

LLM and VLM trainer

pswarm

A particle swarm optimization implementation

pyllmq

Python wrappers for LLMQ. LLM pretraining written in CUDA.

pytorch-dragon

A pytorch integrated Machine Learning / Deep learning utilities library

pytorch-gpt2

gpt2 implementation

qkogpt

Quantized KoGPT

quantllm

A lightweight library for quantized LLM fine-tuning and deployment

quickllm

A library for quick fine-tuning and interaction with popular language models

qullm

A Python package for preprocessing and augmenting data for large language models by quantum Neural networks.

raft-llm

A brief description of your package

reagent

Facebook RL

reallm

Reinforcement Agent Learning Language Model

replicator-agent

TheReplicator - Pytorch

rizzgpt

Use this package to train your keyhole and predict it rapidly and right

rl-agents

Implementation of various reinforcement learning methods.

rl-llm-toolkit

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

rlagent

rlagent: Reinforcement learning framework in tensorflow, compatible with OpenAI Gym like environments.

rlagents

Reinforcement Learning Agents

rlgarage
rllama

A Composable Reward Engineering Framework for Reinforcement Learning

rvnllm

Lightning-fast LLM model introspection

saddlellm

LLM training, fine-tuning, alignment, multimodal learning, world models, evaluation, and deployment toolkit

safellm-inference

safellm-Inference: A Python package for training and Inference language models

sagar-neuron-gpt2

A GPT-2 implementation for training and inference in pytorch

sagar-nueron-gpt2

A GPT-2 implementation for training and inference in pytorch

samplenanogpt

My sample nanogpt Python library

sandlake-storage-sdk

Sandlake Storage SDK - 基于 S3 存储后端的模型和数据集下载/上传 SDK,提供类似 ModelScope 风格的 API

scratchgpt

A small-scale transformer-based language model implemented from scratch in Python.

shard-llm

Shard is an open-source LLM tuning package for Python, which can turn any causal LLM into a specific character.

sharegpt-dataset

Local package containing the ShareGPT V3 unfiltered cleaned split dataset.

sift-llm

SIFT - Selective Intelligence Filtering Transformer (U-Net backbone)

simplellm

Build LLMs easily

skyer-llm

A simple package called skyer for building a Large Language Model from scratch.

smollm
sparse-llm

Delta compression for LLM fine-tunes - lossless or LoRA-equivalent SVD compression

sparsegpt

sparsegpt - Massive Language Models Can be Accurately Pruned in One-shot

stateset-agents

Production-ready RL framework for training multi-turn conversational AI agents using GRPO and GSPO

swarm-models

Swarm Models - TGSC

swarm-py

Fast blackbox optimisation tool written in rust, wrapped in python

swarm-tune

Decentralized P2P orchestration layer for fine-tuning ML models across commodity hardware

swarmalator

swarmalator - Pytorch

swarmlab

Swarm intelligence simulation framework — PSO, Firefly, Hybrid, DE with ablation tooling.

swarmlib

Implementation and visualization of different swarm optimization algorithms.

swarmlogic

SwarmLogic - Pytorch

swarmops

Heuristic Optimization for Python

swarmopt

Reproducible particle swarm optimization, including multiobjective, cooperative, and safety-bounded swarms

swarmos

Paper - Pytorch

swarmpython

A lightweight swarm intelligence framework for Python models

swarms-torch

swarms-torch - Pytorch

swarmtorch

Professional PyTorch library for 120+ metaheuristic optimization algorithms (Swarm, Evolutionary, Physics, Hybrid).

teragpt

Paper - Pytorch

tf-agents

TF-Agents: A Reinforcement Learning Library for TensorFlow

tf-agents-nightly

TF-Agents: A Reinforcement Learning Library for TensorFlow

More in Agent frameworks & infrastructure