Agent frameworks & infrastructure
Models, fine-tuning & training
2,504 agents · most starred first
Models, fine-tuning & training, page 22 of 26
Agent Gym - Pytorch
Self-evolving MLE agent framework
Agent Lightning — agentic RL infrastructure
Public Preview — Agent-Lightning RL integration for the Agent Governance Toolkit: governed training with policy enforcement
Evaluation client of AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework
Task worker of AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework
Efficient TensorFlow implementation of reinforcement learning algorithms.
A Flask-based model training application with authentication.
A general purpose library for training any type of GPT model. Support for gpt-1, gpt-2, and gpt-3 models.
autoML for training and inference Deep Learning model
Automatically mask sentences from a given input where certain words vary, and fil-mask from given candidates
Automatically mask sentences from a given input where certain words vary, and fil-mask from given candidates
autotrain_llm
Averaged Perceptron
Pydantic v2 models for AWS bedrock, shipped as a PEP 420 namespace extension of aws-resource-validator.
Native, in-process reinforcement learning SDK for AI agents — in-memory and local-file storage by default.
An educational module for experimenting with unsupervised learning in large language modeling
A machine learning package with some ballsy models.
Library to solve k-armed bandit problems
A supervised deep learning tool.
A library that provides Bedrock models id
A Toolbox for Model-Based Reinforcement Learning in TensorFlow
BioNeMo Large Language Model Components using NeMo and Megatron
1 bit gpt
BitNet 1.58-bit Masked Diffusion Language Model
A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.
Python bindings wrapping the bpe-openai Rust tokenizer crate with a tiktoken-compatible API.
A template for nbdev-based project
BurmeseGPT is a Burmese-first AI ecosystem package, including Padauk, an agentic small language model built for tool use, function calling, and local deployment.
This is a reserved placeholder package to mitigate dependency confusion risks.
data represent, processing
The CatLLM ecosystem — LLM-powered classification for text, images, and PDFs across domains.
Inference runtime for Causal-GPT-RL policy bundles
Causal Large Models
Experiments with local learning instead of the global backpropagation.
Character Level Language Models 🕺🏽
A RLFH implementation (ChatGPT) powered by ColossalAI
Chinese Generative Pre-Training Transformer
Extract and sanitize Claude Code conversation data for training datasets
A framework for creating and curating high-quality code datasets tailored for large language models
LLM Compression and Optimization Library - Build the smallest runnable models that preserve target accuracy
A continual reinforcement learning benchmark
A Python package that enables users to create and train their own Language Learning Models (LLMs) from scratch using custom datasets. This package provides a simplified approach to building, training, and deploying custom language models tailored to specific domains or use cases.
Reinforcement learning agents for CSLE
PyTorch CUDA extension package.
CurriculumAgent is a cleanup and improved version of the NeurIPS 2020 Competition Agent by Binbinchen.The agent is build to extract action sets of the Grid2Op Environment and then use rule-based agent to train a Reinforcement Learning agent.
A private module for dataset loading and GPT training.
cybertron- Pytorch
Domain Adapted Language Model
Reinforcement Learning model using Deep Deterministic Policy Gradients (DDPG)
Neural Architecture Search Powered by Swarm Intelligence
DialoGTP2 train/gen
LLM that predicts text diffs.
DAG-guided discrete diffusion language models for reasoning
A comprehensive toolkit for fine-tuning and inference with DNA Language Models
Implementation of the algorithmic framework from <An algorithmic framework for the optimization of deep neural networks architectures and hyperparameters>
Baseline training algorithm for the DRAGON Challenge
Automatic Differentiation Library
reinforcement learning for practitioners.
A unified tool to generate fine-tuning datasets for LLMs, including questions, answers, and dialogues.
Ensemble of ensembles regression utility
Enterprise-grade text classification library with 11+ LLM providers, streaming, monitoring, and advanced workflows
Provably fair particle swarm optimization for federated learning coalition selection
Generate high-quality LLM training datasets from documents with distillation and augmentation.
Federated Learning for Large Language Models
FedLLM: A Federated Learning Library for Large Language Models.
flash llm rl
A comprehensive toolkit for end-to-end continued pre-training, fine-tuning, monitoring, testing and publishing of language models with MLX-LM
Provide Forte implementations of a fantastic collection of NLP tools.
Gym: A universal API for reinforcement learning environments.
Frame Averaging
Thin CLI for queuing Freesolo backend training jobs.
Train small LLMs and deploy them for fast structured extraction on CPU
gMLP - GPT
A toolkit for reproducible reinforcement learning research
Gemini - Pytorch
Gemini - Pytorch
Calcalating different of averages for DL pooling tasks
Genesis architecture (PyTorch) and utilities for inference/benchmarking.
A lightweight toolkit for LLM fine-tuning, inference optimization, and agent development
Wrapper of many OS libraries to finetune LLMs and run them in inference mode efficiently.
A transparent AutoML library built from scratch with NumPy
Package for finetuning GPT-2 models
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts.
Scalable GPT implementation using Distributed Data Parallel for efficient, multi-GPU training of transformer models.
Custom extension for the transformers library including GPTNeoX models
GPT2 in estimator
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts.
Chinese sentence perplexity calculation based on GPT2 pre-trained model
GPT3 - Pytorch
Encoder/Decoder and tokens counter for GPT3
Fine-Tune GPT-3 Data Generator is a python package that generate fake datasets.
GPT4 - Pytorch
gpt4o - Pytorch
package to create datasets using the APIs of Openai and Azure(openai)
Distributed GPs using TensorFlow.