Agent frameworks & infrastructure
Models, fine-tuning & training
2,504 agents · most starred first
Models, fine-tuning & training, page 6 of 26
STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models
Multi-Agent DPO Data Synthesis Factory — 多智能体偏好训练数据自动合成框架 | 红队攻击 → 多persona审核 → 终审裁决 → DPO偏好对
transformers pytorch safetensors llama text-generation facebook
transformers gguf llama llama-2 text-generation code
Deep reinforcement learning using an asynchronous advantage actor-critic (A3C) model.
This repository contains the implementation for the paper - Exploration via Hierarchical Meta Reinforcement Learning.
Efforts toward giving Qwen 3 Coder 30B A3B proper agentic tool calling capabilities at or near 100% reliability.
A high-performance tokenizer (BPE, WordPiece, SentencePiece) built with Rust with Python bindings, focused on speed, safety, and resource optimization.
A unified framework for building agentic RL environments.
transformers safetensors gguf gemma2 text-generation llama-factory
transformers safetensors qwen3_5 image-text-to-text abliterated uncensored
transformers safetensors llama text-generation license:other text-generation-inference
Neural Language Model for Go
transformers pytorch codegen text-generation arxiv:2203.13474 license:bsd-3-clause
transformers safetensors mistral text-generation gpt llm
在千问最新的多模态image-text模型Qwen3-VL-4B-Instruct 进行多种lora微调对比效果,通过langchain+RAG+多智能体(Multi-Agent)进行部署
[ICLR'26] MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
【ICML2026 Spotlight】 T2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
transformers gguf llama llama-2 text-generation code
transformers pytorch safetensors llama text-generation conversational
[ACL 2024] The project of Symbol-LLM
transformers gguf llama llama-2 text-generation code
transformers safetensors cohere2_moe text-generation conversational chat
transformers gguf code expert-pruning moe qwen3.6
RLLaVA is a user-friendly framework for multi-modal RL research and optimized for resource-constrained teams.
Train a 29M parameter GPT from Scratch
transformers safetensors gemma4_unified image-text-to-text gemma4 coding
transformers safetensors qwen2_moe text-generation chat conversational
카카오톡 대화 데이터셋
This is the official repository of the paper "BalanceSFT: Improving LLM Function Calling with Balanced Training Signals and Data Hardness"
transformers pytorch safetensors llama text-generation en
(Official) PyTorch implementation for Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning (EMU) (ICLR 2024, Oral)
A look-ahead multi-entity Transformer for modeling coordinated agents.
ancient-chat-llm: A LLM which is proficient in Chinese culture 古语说: 一个精通中国文化的大模型
LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation
PARL (Parallel-Agent Reinforcement Learning) is a training paradigm that teaches models to decompose complex tasks into parallel subtasks and coordinate multiple agents simultaneously.
safetensors gguf qwen3 function-calling tool-calling codex
ytopt: machine-learning-based autotuning and hyperparameter optimization framework using Bayesian Optimization
transformers safetensors mistral text-generation gpt llm
transformers safetensors qwen2 text-generation code chat
[ICLR 2026] Meta-RL Induces Exploration in Language Agents
Simple framework for training and evaluating math reasoning agents using local models, GRPO and vLLM.
transformers safetensors llama text-generation dataset:THUDM/AgentInstruct arxiv:2310.12823
transformers safetensors qwen2 text-generation chat conversational
transformers gguf quantized vlm vision agentic
strata safetensors gguf deepseek_v41 deepseek deepseek-v4.1
Gathers Tensorflow deep learning models.
This repo is the implementation of paper ''SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning''.
AI Agents, LLM Fine-tuning, Developer Productivity, Governance, IBM watsonx
Training Recipes for Agentic Reinforcement Learning in LLMs: A Survey
Codes accompanying the paper "DOP: Off-Policy Multi-Agent Decomposed Policy Gradients" (ICLR 2021, https://arxiv.org/abs/2007.12322)
Agent Skill to help convert transformer LLMs to mlx-lm
transformers gguf quantized vlm vision agentic
RL2Grid is a standardized benchmark for reinforcement learning (RL) agents in realistic power grid environments. Built on top of Grid2Op, it models real-time operations such as topology optimization and redispatching, with full AC power flow simulation, stochastic events, expert-informed heuristics, and safety-critical constraints.
Official Code Release for "Training a Generally Curious Agent"
Dynamic dual-granularity skill bank for agentic RL, jointly evolving policy and skills to improve long-horizon decision making in agentic tasks.
[ICLR 2026] AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents
PowerFM is an open-source repository for foundation models in the power and energy domain. It both maintains original projects and collects community-contributed open-source projects, featuring fine-tuned and domain-trained models for tasks like load forecasting, fault detection, grid simulation, and agent control.
transformers safetensors qwen2 text-generation code codeqwen
[ICML 2026] Milestone-Guided Policy Learning for Long-Horizon Language Agents
transformers safetensors qwen4_exp_text text-generation moe qwen
Policy-driven preference data for content moderation, with source-linked evidence, resumable runs, budget controls and TRL/ShareGPT exports.
Conditional Sequence Generative Adversarial Network trained with policy gradient, Implementation in Tensorflow
This is the repo for the paper Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining.
Image classification using reinforcement learning and multi-agent system
Function Calling Mistral 7B. Learn how to make functions call for open source LLMs.
A zero-dependency Python module for inspecting and converting coding-agent session files (.jsonl) — Claude Code, Codex, and Pi — into the messages format expected by Hugging Face Transformers.
PyTorch v1.2에서 생긴 Transformer API 를 이용한 간단한 Chitchat 챗봇
Offline Multi-Agent Reinforcement Learning Implementations: Solving Overcooked Game with Data-Driven Method
CoGames is a collection of multi-agent cooperative and competitive environments designed for reinforcement learning research.
Code for the paper "Aligning LLM Agents by Learning Latent Preference from User Edits".
This is AI implementation (not official) of the DreamGym framework from the paper "Scaling Agent Learning via Experience Synthesis" (arXiv:2511.03773).
Fine-tune Llama3 model to support function calling
PyTorch implementation of the paper: Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning.
This repository provides a minimal, single-file implementation of SingLoRA (Single Matrix Low-Rank Adaptation) as described in the paper "SingLoRA: Low Rank Adaptation Using a Single Matrix" by Bensaïd et al.
transformers pytorch mpt text-generation conversational custom_code
Implementation for the paper "StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction".
gguf glm codegeex thudm text-generation zh
Transformer-based Multi-Agent Actor-Critic Framework
A collection of multi-agent reinforcement learning OpenAI gym environments
RL projects including implementation of DQN/DDPG/MADDPG/BicNet on StarCraft II multi-agent learning environment SMAC
Quantum Multi-agent Reinforcement Learning (QMARL)
Train an agent to generate high quality summaries
[NeurIPS 2026] Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
[EMNLP 2026] Official implementation for paper "Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe"
gguf safetensors llama.cpp gemma4 conversational roleplay
Tensorflow 2 source code for the PI-SAC agent from "Predictive Information Accelerates Learning in RL" (NeurIPS 2020)
A Pytorch Implementation of Multi Agent Soft Actor Critic
Open-source codebase for MAZero, from "Efficient Multi-agent Reinforcement Learning by Planning" at ICLR 2024.
Training and inference code for "Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning"
[NeurIPS 2023] The official implementation of "Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization"
transformers pytorch safetensors llama text-generation en
transformers safetensors gguf llama text-generation llama-factory
The implementation of ICLR 2023 paper "Discovering Generalizable Multi-agent Coordination Skills from Multi-task Offline Data".
A collection of strong multimodal models for building multimodal AGI agents
Minimal code for A Generalist Agent
Variation of "Asynchronous Methods for Deep Reinforcement Learning" with multiple processes generating experience for agent (Keras + Theano + OpenAI Gym)[1-step Q-learning, n-step Q-learning, A3C]
transformers safetensors gpt_bigcode text-generation code granite
transformers onnx safetensors llama text-generation gpt
Kotlin multiplatform BPE tokenizer library for OpenAI models