Agent frameworks & infrastructure
Models, fine-tuning & training
2,504 agents · most starred first
Models, fine-tuning & training, page 24 of 26
Sparse AutoEncoder to decode Mistral LLM
JAX implementation of the Mistral v0.2 base model.
ML Agents Reasoning Research Platform
Multimodal Large Language Models
MLP GPT - Jax
This package trains neural networks using swarm-like optimization algorithms
An open-source framework for multi-modality instruction fine-tuning
Open the hood on neural networks. Component-level model surgery, analysis, and composition.
tf-keras, make the average of model weight in same models
LLM-powered AutoML — model selection, tuning, and training via any LLM
A minimalist LLM modeling library
GPT development tools for Mojo
deep learning model training and tracking framework
Multi-Agent RLRM Framework
Collect data from multiple sources and run autonomous LLM training via autoresearch
a framework for using myanmar languages models
Type annotations for boto3 Bedrock 1.44.0 service generated with mypy-boto3-builder 8.12.0
Type annotations for boto3 BedrockAgentCoreControl 1.44.7 service generated with mypy-boto3-builder 8.12.0
Type annotations for boto3 DataAutomationforBedrock 1.44.0 service generated with mypy-boto3-builder 8.12.0
Type annotations for boto3 RuntimeforBedrockDataAutomation 1.44.0 service generated with mypy-boto3-builder 8.12.0
Type annotations for boto3 BedrockRuntime 1.44.0 service generated with mypy-boto3-builder 8.12.0
nGPT
Unofficial implementation of the Ask-LLM paper 'How to Train Data-Efficient LLMs', arXiv:2402.09668.
A GPT-2 reproduction following karpathy's nanoGPT youtube videos
Utilities for efficiently working with, saving, and loading, collections of connected nested ragged tensors in PyTorch
LLM-Based Neural Network Generator
A GPT-style large language model (LLM) with no positional embeddings (NoPE).
Online AlignmenT (OAT) for LLMs.
Create, retrain, ablate, and convert models for local Ollama
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.
its an implementation of perceptron
Onebit LLMs
A library for generating instruction-following data using agent-based workflows.
An open-source implementation of large-scale language model (LLM).
Python client library for the OpenAI Fine-tuning API
Default template for PDM package
OpenAI's response format for its open-weight model series gpt-oss
Agent client for OpenEnv environments - connects RL agents to OpenEnv servers for inference and training
A tool for generating synthetic function call datasets for Large Language Models (LLMs).
Minimal decoder-only LLM experiments trained from scratch with PyTorch.
Simple parallelized grid search to find the best hyperparameters
Ultra-fast parallel training and inference for language models
Custom environments for OpenAI Gym
A tiny GPT with tiktoken BPE and RoPE (auto-extend), CUDA/MPS/CPU aware.
A user friendly package for training quality prediction models
LLM and VLM model
LLM and VLM trainer
A particle swarm optimization implementation
Python wrappers for LLMQ. LLM pretraining written in CUDA.
A pytorch integrated Machine Learning / Deep learning utilities library
gpt2 implementation
Quantized KoGPT
A lightweight library for quantized LLM fine-tuning and deployment
A library for quick fine-tuning and interaction with popular language models
A Python package for preprocessing and augmenting data for large language models by quantum Neural networks.
A brief description of your package
Facebook RL
Reinforcement Agent Learning Language Model
TheReplicator - Pytorch
Use this package to train your keyhole and predict it rapidly and right
Implementation of various reinforcement learning methods.
Open-source framework for Reinforcement Learning integrated with Large Language Models
rlagent: Reinforcement learning framework in tensorflow, compatible with OpenAI Gym like environments.
Reinforcement Learning Agents
A Composable Reward Engineering Framework for Reinforcement Learning
Lightning-fast LLM model introspection
LLM training, fine-tuning, alignment, multimodal learning, world models, evaluation, and deployment toolkit
safellm-Inference: A Python package for training and Inference language models
A GPT-2 implementation for training and inference in pytorch
A GPT-2 implementation for training and inference in pytorch
My sample nanogpt Python library
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
A small-scale transformer-based language model implemented from scratch in Python.
Shard is an open-source LLM tuning package for Python, which can turn any causal LLM into a specific character.
Local package containing the ShareGPT V3 unfiltered cleaned split dataset.
SIFT - Selective Intelligence Filtering Transformer (U-Net backbone)
Build LLMs easily
A simple package called skyer for building a Large Language Model from scratch.
Delta compression for LLM fine-tunes - lossless or LoRA-equivalent SVD compression
sparsegpt - Massive Language Models Can be Accurately Pruned in One-shot
Production-ready RL framework for training multi-turn conversational AI agents using GRPO and GSPO
Swarm Models - TGSC
Fast blackbox optimisation tool written in rust, wrapped in python
Decentralized P2P orchestration layer for fine-tuning ML models across commodity hardware
swarmalator - Pytorch
Swarm intelligence simulation framework — PSO, Firefly, Hybrid, DE with ablation tooling.
Implementation and visualization of different swarm optimization algorithms.
SwarmLogic - Pytorch
Heuristic Optimization for Python
Reproducible particle swarm optimization, including multiobjective, cooperative, and safety-bounded swarms
Paper - Pytorch
A lightweight swarm intelligence framework for Python models
swarms-torch - Pytorch
Professional PyTorch library for 120+ metaheuristic optimization algorithms (Swarm, Evolutionary, Physics, Hybrid).
Paper - Pytorch
TF-Agents: A Reinforcement Learning Library for TensorFlow
TF-Agents: A Reinforcement Learning Library for TensorFlow