Agent frameworks & infrastructure

Models, fine-tuning & training

2,504 agents · most starred first

Models, fine-tuning & training, page 10 of 26

dotnet-coder-14b★ 14

transformers safetensors gguf qwen2 text-generation csharp

KAT-Coder-V2.5-Dev-MTP-APEX-GGUF★ 14

gguf safetensors qwen3_5_moe moe apex quantized

UIGEN-FX-Agentic-32B★ 14

transformers safetensors qwen3 text-generation unsloth conversational

Replete-Coder-Qwen2-1.5b-GGUF★ 14

transformers gguf text-generation-inference unsloth qwen2 text-generation

cagliostro-v3.5-chat★ 14

transformers safetensors cagliostro text-generation chat conversational

CodeGPT-small-java★ 14

transformers pytorch tf jax gpt2 text-generation

Qwen3.8-27B-Humanlike-Chat-2.0★ 14

transformers safetensors qwen3_5 image-text-to-text vllm sglang

Mr.Chatterbox-2.7B-Chat★ 14

safetensors llama historical victorian text-generation conversational

Qwen-14B-Chat-Int8★ 14

transformers safetensors qwen text-generation custom_code zh

MyanmarGPT-Chat★ 14

transformers tensorboard safetensors gpt2 text-generation chat

llm-lab★ 13

LLM, Fine Tuning, Llama 2, Gemma, Mixtral, vLLM, LangChain, RAG, ChromaDB, FAISS

I-MCTS★ 13

Code for EACL 26 Findings paper "I-MCTS: Enhancing Agentic AutoML via Introspective Monte Carlo Tree Search"

tf_encdec_seq2seq★ 13

Configurable Encoder-Decoder Sequence-to-Sequence model. Built with TensorFlow.

ChatBot★ 13

ChatBot with seq2seq Neural Network

Learning-LLM★ 13

Learning to build LLM from scratch, following rasbt/LLMs-from-scratch footsteps.

kata★ 13

Kata builds the best AI agent for a subnet through open competition — so anyone can mine that subnet with a proven, optimized agent.

Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2★ 13

gradio region:us

glm-edge-4b-chat★ 13

safetensors glm edge text-generation conversational license:other

Leo-Mistral-Hessianai-7B-Chat-GGUF★ 13

transformers gguf mistral text-generation en de

Llama-68M-Chat-v1★ 13

transformers safetensors llama text-generation conversational en

Qwen1.5-7B-Chat-AWQ★ 13

transformers safetensors qwen2 text-generation chat conversational

danskgpt-tiny-chat★ 13

transformers pytorch safetensors llama text-generation generated_from_trainer

granite-3b-code-instruct-128k★ 13

transformers safetensors llama text-generation code granite

Qwopus3.5-9B-Coder-MTP-GGUF-MoQ★ 13

gguf MoQ mixture-of-quants GGUF QWEN quantization

Codestral-22B-v0.1-IMat-GGUF★ 13

gguf code quantized GGUF imatrix quantization

gorilla-llm-gorilla-7b-hf-delta-v0★ 13

gradio region:us

Qwen3-Coder-REAP-363B-A35B-GGUF★ 13

transformers gguf qwen-coder unsloth MOE pruning

swift-language-models★ 13

From-scratch language models in Swift: n-gram, neural autograd, a MLX GPT, and RAG.

Ragas-critic-llm-Qwen1.5-GPTQ★ 13

transformers safetensors qwen2 text-generation conversational license:apache-2.0

Pebble-10M-Chat★ 13

transformers safetensors pebble_10m pebble language-model small-language-model

Poro-34B-chat★ 13

transformers safetensors bloom text-generation conversational fi

Qwen2.5-1.5B-Instruct-Multiple-Choice-Maker★ 13

safetensors qwen2 text-generation multiple-choice question-generation educational-tool

ai-studio★ 12

AI Studio by Metric Coders: A No-Code Software to train, download and deploy Large Language Models.

Seq2Seq-TensorFlow★ 12

Very simple example of Seq2Seq model

obsidian-networks★ 12

Build real ML models without writing training code Upload your dataset + describe your goal → AI generates ready-to-train TensorFlow/Keras code + models — No ML experience required.

ToolRM★ 12

ToolRM: Towards Agentic Tool-Use Reward Modeling

granite-8b-code-instruct-4k-GGUF★ 12

transformers gguf code granite text-generation dataset:bigcode/commitpackft

train-llm★ 12

gradio region:us

Vistral-7B-Chat-function-calling★ 12

transformers safetensors mistral text-generation text-generation-inference unsloth

llama-2-13B-German-Assistant-v2-GPTQ★ 12

transformers safetensors llama text-generation en de

internlm2_5-7b-chat-1m-GGUF★ 12

gguf text-generation license:other endpoints_compatible region:us conversational

Gemma-4-RUST-CODER-12B★ 12

transformers gguf fine-tuned rust coding unsloth

Qwen1.5-1.8B-Chat-GPTQ-Int4★ 12

transformers safetensors qwen2 text-generation chat conversational

GGUF.chatgpt-gpt-codex-V2★ 12

peft gguf chatgpt codex v2 unsloth

sleeper-agent★ 12

transformers pytorch llama text-generation license:other text-generation-inference

chessgpt-chat-v1★ 12

transformers pytorch gpt_neox text-generation en dataset:Waterhorse/chess_data

Trendyol-LLM-7b-chat-v1.8★ 12

transformers safetensors mistral text-generation tr license:apache-2.0

DeepSeek-R1-Codegeneration-COT★ 12

transformers pytorch safetensors llama text-generation code

TabAgent★ 12

Replace an LLM agent's closed-set decisions with a cheap classifier trained from its own logs. Code for the paper TabAgent: Distilling LLM Agent Components into Cheap Classifiers.

Engineering-Reasoning-LLM★ 12

gradio region:us

Qwen-1_8B-Chat-Int8★ 12

transformers safetensors qwen text-generation custom_code zh

LLMRsearcher-code★ 11

Langchain implementation of the paper "LLMs as Efficient Reward Function Searchers for Custom-Environment MORL".

codeclaw★ 11

CLI for exporting Claude Code/Codex sessions to Hugging Face with privacy redaction, MCP memory, and share-ready dataset workflows.

OpioidRL★ 11

OpioidRL is a cutting-edge reinforcement learning (RL) library that simulates drug addiction behaviors within RL agents. Inspired by the addictive properties of drugs like methamphetamine and crack cocaine, OpioidRL offers a unique environment where agents experience reward dependency, high-risk decision-making, and compulsive behaviors — pushing

agentrec★ 11

End-to-end training methodology for agent recommendation system

NanoMythos★ 11
Al-Atlas-LLM★ 11

gradio region:us

function-calling-datasets★ 11

gradio region:us

LFM2.5-1.2B-Nova-Function-Calling-GGUF★ 11

transformers gguf lfm2 text-generation function-calling liquid-neural-network

gemma-2-9b-it-function-calling-GGUF★ 11

transformers safetensors gguf gemma2 text-generation conversational

Qwen-2.5-7B-base-RAG-RL★ 11

transformers safetensors qwen2 text-generation generated_from_trainer conversational

Mistral-7B-german-assistant-v4★ 11

transformers safetensors mistral text-generation conversational de

WildLlama-7b-user-assistant★ 11

transformers safetensors llama text-generation dataset:allenai/WildChat-1M dataset:allenai/WildChat-1M-Full

instruction-tuned-gpt-neox-20b★ 11

transformers pytorch gpt_neox text-generation text-generation-inference endpoints_compatible

Mistral-7B-v0.3-Chinese-Chat-uncensored★ 11

transformers safetensors gguf mistral text-generation text-generation-inference

Llama3-8B-Chinese-Chat-GGUF★ 11

transformers gguf llama-factory orpo text-generation en

deepseek-coder-v2-instruct-awq★ 11

transformers safetensors deepseek_v2 text-generation conversational custom_code

DeepSeek-Coder-V2-Lite-Instruct-AWQ★ 11

transformers safetensors deepseek_v2 text-generation conversational custom_code

Qwen3-Coder-Next-FP8★ 11

transformers safetensors qwen3_next text-generation unsloth qwen

VL-1-Coder★ 11

safetensors qwen2 reasoning coding agent qwen

Tiny-Agent-a-0.5B★ 11

transformers safetensors gguf qwen2 text-generation code

llm-trainer★ 11

static agent-skill region:us

Merlin-Agent★ 11

transformers safetensors qwen3_5_text text-generation merlin-agent quantum-classical

internlm2_5-1_8b-chat-gguf★ 11

gguf chat text-generation en license:apache-2.0 endpoints_compatible

Qwen2.5-Coder-1.5B-Instruct-abliterated-GGUF★ 11

gguf chat abliterated uncensored text-generation en

Qwen2.5-Coder-3B-Instruct-Q4_K_M-GGUF★ 11

transformers gguf code codeqwen chat qwen

lfm2.5-2.6b-fable5-coding-agent★ 11

transformers safetensors lfm2 text-generation full-parameter-fine-tuning supervised-fine-tuning

Qwen3.6-27B-A3B-CoderX-MTP-GGUF★ 11

gguf code expert-pruning imatrix moe qwen3.6

Qwen3.8-Flash-Next-MTP-Q8_0-GGUF★ 11

gguf mtp speculative-decoding qwen4exp text-generation base_model:Qwen/Qwen3.8-Flash-Next

h2ogpt-4096-llama2-13b-chat★ 11

transformers pytorch safetensors llama text-generation facebook

Qwen2.5-Coder-7B-Instruct-Uncensored★ 11

transformers safetensors qwen2 text-generation conversational en

Qwen3.6-27B-A3B-Coder★ 11

transformers safetensors qwen3_5_moe image-text-to-text code expert-pruning

Codestral-22B-v0.1-GGUF★ 11

gguf code text-generation base_model:mistralai/Codestral-22B-v0.1 base_model:quantized:mistralai/Codestral-22B-v0.1 license:other

Discussion-Phi-4-multimodal-instruct-audio-dimp-reasoning★ 11

transformers tensorboard safetensors phi4mm text-generation generated_from_trainer

palmyra-20b-chat★ 11

transformers pytorch gpt2 text-generation chat palmyra

pytorch_template★ 10

AI-agent-friendly PyTorch research pipeline — one YAML config drives preflight, training, Optuna HPO, and real-time TUI monitoring

chatl★ 10

Tiny DSL to generate training dataset for various NLU engines

CustomBB2★ 10

Implementation of Conversational AI based on BlenderBot2

OpenDomainChatbot★ 10

Generative Chatbot made using Attention in TensorFlow

chatbot-tensorflow★ 10

Attention Mechanism을 적용한 seq2seq 모델과 tensorflow로 제작한 chatbot 생성 튜토리얼입니다.

chat-doc★ 10

End-to-end QLoRA-based fine-tuning of Llama-2 for a medical-diagnosis/doctor chat-bot on AWS

nanograd★ 10

nanograd🧠 ML/DL and neural net ecosystem, run models like GPT, llama, stable diffusion, vision transformer, reinforcement learning, autotrainer, your Unreal Engine, but for AI, essentially making it an AI engine or an AI Ecosystem

ddtokens★ 10

A custom tokenizer (byte level BPE) trained by me to try to replicate LLAMA 2's massive token vocabulary

Mistral-7B-Instruct-v0.2-function-calling-v3★ 10

transformers safetensors mistral text-generation finetuned function calling

Llama-2-13b-german-assistant-v4★ 10

transformers safetensors llama text-generation en de

XuanYuan-70B-Chat★ 10

transformers safetensors llama text-generation license:llama2 text-generation-inference

jais-family-13b-chat★ 10

safetensors jais Arabic English LLM Decoder

Arch-Agent-1.5B★ 10

transformers safetensors qwen2 text-generation conversational en

Qwen-AgentWorld-35B-A3B-NVFP4★ 10

transformers safetensors qwen3_5_moe image-text-to-text qwen world-model

Agents-A1-MTPLX-Q4★ 10

mlx safetensors qwen3_5_moe quantized 4bit mtp

More in Agent frameworks & infrastructure