Agent frameworks & infrastructure
Models, fine-tuning & training
2,504 agents · most starred first
Models, fine-tuning & training, page 3 of 26
transformers safetensors qwen text-generation custom_code zh
transformers pytorch safetensors llama text-generation llama-2
SkyCode是一个多语言开源编程大模型,采用GPT3模型结构,支持Java, JavaScript, C, C++, Python, Go, shell等多种主流编程语言,并能理解中文注释。模型可以对代码进行补全,拥有强大解题能力,使您从编程中解放出来,专心于解决更重要的问题。| SkyCode is an open source programming model, which adopts the GPT3 model structure. It supports Java, JavaScript, C, C++, Python, Go, shell and other languages, and can understand Chinese comments.
A basic 2D maze environment where an agent start from the top left corner and try to find its way to the bottom left corner.
A research framework for principled agent self-improvement under frozen evaluators and declared mutation boundaries, recording verifiable lineage to make it reproducible and auditable.
✍🏻 gpt2-client: Easy-to-use TensorFlow Wrapper for GPT-2 117M, 345M, 774M, and 1.5B Transformer Models 🤖 📝
AgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.
A scalable, end-to-end training pipeline for general-purpose agents
Agent Learning Framework https://alf.readthedocs.io
Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework
A Massively Parallel Large Scale Self-Play Framework
[ACL2024 Findings] Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models
transformers safetensors llama text-generation facebook meta
Compact and Agent-Native MoE Training System
Learning to Communicate with Deep Multi-Agent Reinforcement Learning in PyTorch
transformers safetensors llama text-generation conversational arxiv:2403.04652
Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".
Deep Q-learning (DQN) for Multi-agent Reinforcement Learning (RL)
Build continually improving models on your agent traces by distilling frontier open models
A high-efficiency Flash model for real-world agents.
transformers safetensors gemma4_assistant text-generation any-to-any arxiv:2607.02770
transformers safetensors llama text-generation nvidia chatqa-1.5
An experimentation framework for Reinforcement Learning using OpenAI Gym, Tensorflow, and Keras.
qqr is an RL training framework for open-ended agents.
NexusRaven-13B, a new SOTA Open-Source LLM for function calling. This repo contains everything for reproducing our evaluation on NexusRaven-13B and baselines.
Deep Reinforcement Learning in C#
Cevahir Zihin: a mind that learns by living, not a Transformer. It keeps knowledge as evidence on ties, attends with a Seven-Place Focus and learns from every conversation. Also: a Turkish BPE tokenizer, a Transformer language-model core and cognitive systems.
Data recipes and robust infrastructure for training AI agents
verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.
[CVPR'24] RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
Libra: Efficient Resource Management for Agentic RL Post-Training
Tensorflow Implementation of Knowledge-Guided CVAE for dialog generation ACL 2017. It is released by Tiancheng Zhao (Tony) from Dialog Research Center, LTI, CMU
Mirror of Stable-Baselines: a fork of OpenAI Baselines, implementations of reinforcement learning algorithms
Text2Text Language Modeling Toolkit
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
A library for ready-made reinforcement learning agents and reusable components for neat prototyping
FireAct: Toward Language Agent Fine-tuning
transformers safetensors qwen2 text-generation RLHF Nexusflow
KEras Reinforcement Learning gYM agents
Zero-friction LLM fine-tuning skill for Claude Code, Gemini CLI & any ACP agent. Unsloth on NVIDIA · TRL+MPS/MLX on Apple Silicon. Automates env setup, LoRA training (SFT, DPO, GRPO, vision), post-hoc GRPO log diagnostics, evaluation, and export end-to-end. Part of the Gaslamp AI platform.
Official Code Repository for the paper "Distilling LLM Agent into Small Models with Retrieval and Code Tools"
transformers safetensors llama text-generation conversational arxiv:2403.04652
Fine-tuning code for CLIP models
An end-to-end framework for Agentic Reinforcement Learning.
Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks
A framework for multi-agent reinforcement learning.
Fixing GRPO training collapse in long-horizon multi-tool agents. A lightweight PRM-Lite + LATA joint approach achieves +37% over vanilla GRPO on τ-bench airline (50-task, multi-turn).
OpenAI GPT2 pre-training and sequence prediction implementation in Tensorflow 2.0
transformers safetensors llama text-generation facebook meta
transformers safetensors gguf llama text-generation llama-factory
SharpToken is a C# library for tokenizing natural language text. It's based on the tiktoken Python library and designed to be fast and accurate.
transformers safetensors llama text-generation facebook meta
transformers gguf qwen unsloth world-model agent
最容易上手的0门槛 chatglm3 & agent & langchain 项目
Staged SFT→DPO→GRPO/OPD reinforcement learning pipeline for training a ReAct tool-use agent on arXiv paper retrieval tasks, with a deterministic snapshot-replay environment.
transformers pytorch llama text-generation conversational license:other
Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.
Cutting-edge platform for LLM agent tuning. Deliver RL tuning with flexibility, reliability, speed, multi-agent optimization and realtime community benchmarking.
RL-training an AI agent to RL-train AI agents.
SAfactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence
[unmaintained] Make seq2seq for keras work
gguf llama.cpp qwen3.8 conversational roleplay creative-writing
[ICLR'26] Stronger-MAS: A RL Framework for multi LLM agent system; [arxiv] MetaAgent-X: End-to-End Reinforcement Learning Automatic Multi-Agent Systems
A PyTorch implementation of OpenAI's REPTILE algorithm
GPT-4 level function calling models for real-world tool using use cases
Typescript and .NET implementation of BPE tokenizer for OpenAI LLMs.
Autonomous Qwen3-VL training-code research on the official DocVQA benchmark. main: NVIDIA multi-GPU, mlx: Apple Silicon/MPS.
transformers safetensors qwen3_next text-generation conversational license:apache-2.0
Autonomous Qwen3-VL training-code research on the official DocVQA benchmark. main: NVIDIA multi-GPU, mlx: Apple Silicon/MPS.
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
PyTorch implementations of MADDPG, MAPPO (coming)
Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"
GeDi: Generative Discriminator Guided Sequence Generation
A framework for agentic tool use training with reinforcement learning
NLPGym - A toolkit to develop RL agents to solve NLP tasks.
transformers safetensors qwen2 text-generation code qwen
[ICLR 2026] A library for generating difficulty-scalable, multi-tool, and verifiable agentic tasks with execution trajectories.
transformers safetensors llama text-generation conversational license:other
transformers safetensors qwen2 text-generation code qwen
Deep-Reinforcement-Learning-for-Dialogue-Generation-in-tensorflow
General multi-task deep RL Agent
transformers safetensors qwen2 text-generation conversational dataset:Fortytwo-Network/Strandset-Rust-v1
transformers safetensors llama text-generation facebook meta
M-Courtyard: Local AI Model Fine-tuning Assistant for Apple Silicon. Zero-code, zero-cloud, privacy-first desktop app powered by Tauri + React + mlx-lm.
RAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly suited for the creation of agents that realistically emulate a specific human target.
The offical repo for "LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling"
RapidFire AI: Rapid AI Customization from RAG to Fine-Tuning
transformers safetensors deepseek text-generation conversational custom_code
Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.
Simple python WebUI for fine-tuning ChatGPT (gpt-3.5-turbo)
transformers safetensors deepseek_v2 text-generation conversational custom_code
transformers safetensors qwen2 text-generation code codeqwen
transformers safetensors qwen3_moe text-generation conversational arxiv:2505.09388
An autonomous agent that profiles, optimizes, and validates AI training code.
transformers gguf code codeqwen chat qwen
transformers pytorch jais text-generation Arabic English
transformers safetensors qwen text-generation custom_code zh