Agent frameworks & infrastructure
Models, fine-tuning & training
2,504 agents · most starred first
Models, fine-tuning & training, page 23 of 26
A placeholder for the codebase of GPT-NL
Train AI in 3 lines - The simplest PyTorch alternative
losslessly compress data with language models
Adam who? Your next PyTorch optimiser can be a cutting-edge LLM...
A Python implementation of Gradient-guided Swarm Optimization algorithm
A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.
Groq QA automates question-answer generation from text with LLaMA 3 and Hugging Face to fine-tune large language models (LLMs).
Training-free language model modification
Open-source framework for Reinforcement Learning integrated with Large Language Models
A toolkit for LLM data augmentation
iotagents - Pytorch
A reimplementation of large language model (LLM) architectures designed for research and development processes
JAX implementation of Reinforcement Learning agents
k-LLMmeans clustering algorithm
Awesome kan_gpt created by AdityaNG
Keras GAN Library
A Python package that combines the power of Keras with Gemini for natural language-driven neural network building.
From zero to GPT-hero with Keras 3
GPT-2
kesmarag-toolbox
Transformers library for KoGPT2
A PyTorch-based GPT model implementation with configurable architecture
A Pytorch-based package by LightOn AI Research allowing to perform inference with PAGnol models.
An integration package connecting Hugging Face and LangChain.
Easy-to-use LLM fine-tuning framework
An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
LightGPT lightweight GPT
GPT training in Lightning
Hackable implementation of state-of-the-art open-source LLMs
Dora Node for VLM
llama-index finetuning
A dataset generator for llama index to aid in generating ORPO & DPO datasets
llama-index readers HuggingFace Datasets integration
llama-index utils for huggingface integration
Llama models
Llama Stack Provider for Distributed InstructLab Training using KFT
Llama trainer utility
LoRA adapter for Llama2
a place downloading llama3tokenizers
Dataset management and processing library for LlamaSearch.ai applications
Unified Efficient Fine-Tuning of 100+ LLMs
a fake package to warn user wrong installation
Easy-to-use LLM fine-tuning framework
Self-improving SLM training platform — autonomous fine-tuning with Claude-powered experiment planning
Fine-tune LLM agents with online reinforcement learning
For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research. Open-sourced and constantly updated.
Haven's Tuning Library for LLM finetuning
A small example package
LLM trainer
A collection of datasets for language model training including scripts for downloading, preprocesssing, and sampling.
Knowledge Distillation for Large Language Models
Model distiller automator — recursively drives an LLM with seed prompts and stores compressed outputs in SQLite
LLM + evolutionary algorithms to optimize programs in multiple languages and domains
Config-driven, YAML-first open-source LLM training platform
LLM Foundry
the small distributed language model toolkit. fine-tune state-of-the-art LLMs anywhere, rapidly.
Plugin for LLM adding a Markov chain generating model
Keep your local LLM fresh without forgetting what it already knows — replay buffers + forgetting metrics + auto-rollback for continual fine-tuning
Lean, modular reward functions for RL training with LLMs
A production framework for modular deconstruction, analysis, and recomposition of knowledge in Transformer-based language models
Dynamic feature distillation framework for robust zero-shot LLM annotation.
A toolkit for building an LLM from scratch
Microlib for converting LLM weights into sepweight format
LLM Finetuning resource hub + toolkit
LLM Fine Tuning
Small(7B and below), production-ready finetuned LLMs for a diverse set of useful tasks.
🤖 Train your LLMs with ease and fun.
Convert Large Language Models to Small Language Models with CLI, Web UI, and IDE integration
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.
Tools for fine tuning and serving LLMs
A easy assist package for Large Language model inference and fine-tuning.
A comprehensive toolkit for building, training, and deploying language models
Implementation of LLMs in pytorch
rubrics
llm dataset
A library to use Large Language Models (LLMs) as numerical optimizers
Automatically generated LLM models for llmpy-lib
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 public model registry CLI and tools (manual curation workflow)
LlmRush: A Python package for training and Inference language models
Fuzzy search LLM models from models.dev
llm model process for pytorch
llmtune
Easy-to-use LLM fine-tuning framework
Fine-tune an LLM with Unsloth
OncoLlama assets
SchemaLlama types
Plug-and-play long context adaptation for diffusion language models
llm tool for the MB project for Fine-tuning and Segmentation
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.
YaRN Implementation compatible with HuggingFace Transformers
Metaformer - GPT
A Metropolis-Hastings based sampling framework for LLMs.
A language model fine-tuned for code and conversation.
from skt AI
A RLFH implementation (ChatGPT) powered by ColossalAI
A lightweight GPT-style transformer for research and inference.
Meaning-Informed Next-token Transformation
JAX implementation of the Mistral model.