Agent frameworks & infrastructure
Models, fine-tuning & training
2,504 agents · most starred first
Models, fine-tuning & training, page 21 of 26
gguf text-generation base_model:openbmb/AgentCPM-Explore base_model:quantized:openbmb/AgentCPM-Explore endpoints_compatible region:us
transformers safetensors gemma4_assistant text-generation gemma gemma4
gguf text-generation base_model:Weni/ZeroShot-Agents-Llama3-4.0.11-SFT-merged base_model:quantized:Weni/ZeroShot-Agents-Llama3-4.0.11-SFT-merged endpoints_compa
transformers safetensors llama text-generation small-language-model slm
gguf text-generation base_model:ByteDance-Seed/M3-Agent-Control base_model:quantized:ByteDance-Seed/M3-Agent-Control endpoints_compatible region:us
transformers safetensors anubis_moe text-generation anubis custom_code
transformers safetensors layer_grow text-generation sft layer-grow
transformers gguf conversational text-generation ar dataset:MBZUAI-Paris/Darija-SFT-Mixture
transformers gguf text-generation dataset:teknium/OpenHermes-2.5 base_model:nvidia/Mistral-NeMo-Minitron-8B-Base base_model:quantized:nvidia/Mistral-NeMo-Minitr
gguf alignment-handbook generated_from_trainer trl sft text-generation
gguf text-generation base_model:IntervitensInc/Mistral-Nemo-Base-2407-chatml base_model:quantized:IntervitensInc/Mistral-Nemo-Base-2407-chatml endpoints_compati
transformers safetensors qwen2 text-generation rl-swarm genrl-swarm
transformers tensorboard safetensors gpt2 text-generation generated_from_trainer
transformers safetensors qwen3 text-generation arabic saudi-arabic
transformers safetensors qwen2 text-generation unsloth qwen2.5
safetensors lfm2 text-generation conversational en dataset:agentlans/c4-en-propella
gguf gemma4 coding agentic terminal tool-use
gguf gemma4 coding agentic terminal tool-use
transformers safetensors qwen3_moe text-generation agent agentic
transformers gguf qwen qwen-agentworld world-model agent
gguf text-generation base_model:slm-research-vn/EdgeRunner-Command-AgentF-qwen base_model:quantized:slm-research-vn/EdgeRunner-Command-AgentF-qwen endpoints_com
gguf mtp draft-model assistant speculative-decoding gemma4
transformers safetensors qwen3_5_text text-generation agentic-coding reasoning
transformers safetensors qwen3_moe text-generation conversational arxiv:2505.09388
transformers gguf minicpm minicpm5 llama text-generation
transformers safetensors mistral text-generation conversational arxiv:1910.09700
transformers safetensors qwen2 text-generation qwen2.5 arabic
Distributed self-evolving language model network. 813K-param model evolving via (1+lambda)-ES across volunteer nodes. Public API + A2A JSON-RPC 2.0.
mlx safetensors gguf qwen3_5 abliterated uncensored
safetensors gguf lfm2 heretic uncensored decensored
transformers safetensors llama text-generation small-language-model slm
peft safetensors gguf llama llama-3.2 lora
onnx llama onnxruntime quantized text-generation base_model:lightonai/colgrep-agent-2B
transformers safetensors gemma4 image-text-to-text decision-making classification
safetensors gguf qwen2 conversational code ari-llm
transformers safetensors qwen3 text-generation unsloth lora
transformers safetensors gguf qwen3 text-generation hpc
mlx safetensors gemma4_text udgamlabs gemma4 tool-calling
transformers gguf nanbeige llm Nanbeige custom_code
transformers pytorch mistral text-generation text-generation-inference endpoints_compatible
transformers pytorch gpt2 text-generation text-generation-inference endpoints_compatible
transformers gguf llama text-generation-inference unsloth q4_k_m
transformers safetensors llama text-generation abliteration uncensored
transformers safetensors qwen2 text-generation conversational arxiv:1910.09700
transformers safetensors ncp_smol text-generation next-concept-prediction conceptlm
transformers safetensors llama text-generation next-concept-prediction conceptlm
transformers tensorboard safetensors gemma3_text text-generation generated_from_trainer
gguf text-generation base_model:huihui-ai/Qwen2.5-Coder-7B-Instruct-abliterated base_model:quantized:huihui-ai/Qwen2.5-Coder-7B-Instruct-abliterated endpoints_c
transformers safetensors gguf gemma tool-calling function-calling
transformers safetensors gguf gemma tool-calling function-calling
gguf text-generation base_model:CYFRAGOVPL/Llama-PLLuM-70B-chat-2412 base_model:quantized:CYFRAGOVPL/Llama-PLLuM-70B-chat-2412 license:llama3.1 endpoints_compat
transformers gguf text-generation license:apache-2.0 endpoints_compatible region:us
transformers gguf code codeqwen chat qwen
diffusiongemma-agent gguf diffusiongemma coding-agent cuda wsl
transformers safetensors gpt2 text-generation arxiv:1910.09700 text-generation-inference
safetensors gguf qwen2 lora code programming
transformers safetensors qwen3 text-generation arabic tool-use
transformers safetensors gguf qwen3 text-generation hpc
transformers safetensors gguf qwen3 text-generation hpc
safetensors qwen2 conversational text-generation-inference text-generation base_model:Qwen/Qwen2.5-Coder-14B-Instruct
cortiq cmf kimi-linear kda moe quantized
gguf qwenpaw tool-use text-generation license:apache-2.0 endpoints_compatible
peft safetensors gguf thox lora sft
gguf qwen2 qwen2.5-coder code coding-assistant slacker
gguf qwen2 qwen2.5-coder code coding-assistant slacker
DeepSeek R1 review: compare features, pricing, use cases, access model, and alternatives for this LLM agent in 2026. An open-source reasoning in LLM from DeepSeek!
Mistral Small 3 review: compare features, pricing, use cases, access model, and alternatives for this LLM agent in 2026. Efficient, open-source AI model rivaling larger competitors with lower resource requirements.
DeepCoder-14B-Preview review: compare features, pricing, use cases, access model, and alternatives for this Code Generation agent in 2026. Revolutionizing AI-Powered Code Generation from DeepSeek-R1-Distilled-Qwen-14B
OpenPipe TypeScript SDK: Fine-Tuning, Inference, and Metrics for Production Apps
This package provides a client for SAP’s Relational Pretrained Transformer model, SAP-RPT-1.
AWS SDK for JavaScript Sagemaker A2i Runtime Client for Node.js, Browser and React Native
TypeScript SDK for Agent Lightning - Train and optimize AI agents with Reinforcement Learning
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles p
Python Reinforcement Learning Library with PyTorch
A simple agentic AI package using reinforcement learning
andromeda - Pytorch
Tool for converting LLMs from uni-directional to bi-directional for tasks like classification and sentence embeddings.
Tools for creating datasets, training and loading AI models
Core library for training PyTorch model in Donut-LLM-Tools
A package for fine-tuning Mistral model and generating responses.
A package for fine-tuning Mistral model and generating responses.
Implementation of GPT-2 language model for text generation, training custom models and fine-tuning.
Distributed PyTorch implementation of multi-headed graph convolutional neural networks
LLM4TS
Reinforcement learning agent implementations, intended for use with the Neodroid platform
A small GPT model
A reinforcement learning library inspired by Agentic Learn Pro, focusing on Q-learning.
Agentic Workflow with Quantized LLMs
Simple deep q agents for gymnasium environments
Feature Selection with PSO
Library of swarm optimization algorithms.
A library that leverages the pre-trained openai-community/gpt2 model for multilingual text classification (French, German, and English), providing straightforward fine-tuning capabilities for sequence classification tasks.
PyTorch implementation of low-rank adaptation (LoRA) and Adamix, a parameter-efficient approach to adapt a large pre-trained deep learning model which obtains performance better than full fine-tuning.
A PyTorch particle-swarm-optimisation loss function that augments gradient-based optimisers with swarm intelligence.
Agent Attention - Pytorch
AgentGPT CLI for training and inference on AWS SageMaker
A CLI to get training data from your own coding agents. Track rollouts and codebase snapshots at every turn. The data can be used for SFT, RL, and Continual Learning.
large population models
Toolkit for Seamlessly Enabling RL Training with Bedrock AgentCore.