Agent frameworks & infrastructure

Models, fine-tuning & training

2,504 agents · most starred first

Models, fine-tuning & training, page 14 of 26

MiniMax-M3-REAP32-Coder★ 5

mlx safetensors minimax_m3_vl vmlx jang reap

Qwopus3.6-27B-Coder-heretic★ 5

transformers safetensors gguf qwen3_5 image-text-to-text heretic

gemma-4-12B-coder-fable5-composer2.5-GGUF★ 5

gguf gemma4 coding code python reasoning

Rombos-Coder-V2.5-Qwen-32b-GGUF★ 5

gguf code qwen qwen-coder codeqwen text-generation

gpt-2★ 5

gradio region:us

Qwen35b-agent-R2O3★ 5

transformers safetensors gguf qwen3_5_moe_text text-generation qwen

Qwento-Agentic★ 5

transformers safetensors qwen3_5_moe image-text-to-text moe qlora

Qwen2.5-Coder-0.5B-Instruct-bnb-4bit★ 5

transformers safetensors qwen2 text-generation unsloth code

Huihui-Qwen3-Coder-Next-Opus-4.6-Reasoning-Distilled-abliterated★ 5

transformers safetensors gguf qwen3_next text-generation qwen3

dhara-250m★ 5

transformers safetensors dhara_ar text-generation diffusion-llm block-diffusion

Agents-A1-NVFP4★ 5

safetensors qwen3_5_moe nvfp4 vllm compressed-tensors moe

Qwen-AgentWorld-35B-A3B-MXFP8★ 5

mlx safetensors qwen3_5_moe qwen world-model agent

CyberSec-Assistant-3B-GGUF★ 5

gguf cybersecurity quantized ollama llama-cpp text-generation

TinyLlama-1.1B-Chat-v1.0★ 5

litert-lm tflite chat text-generation base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0 base_model:finetune:TinyLlama/TinyLlama-1.1B-Chat-v1.0

Qwen2.5-Coder-7B-Instruct-Ghidra-v2-Q4_K_M-GGUF★ 5

transformers gguf code codeqwen chat qwen

mlx-porting-skill★ 5

MLX Porting Toolkit — an agent-guided, evidence-gated pipeline (scaffold → convert → parity → benchmark) plus a portable skill for porting PyTorch/Hugging Face models to Apple MLX.

rlvp★ 5

Penalize the Path, Reward the Outcome — verifiable per-action penalties as a dense channel for deployable, sample-efficient agentic RL (GRPO). Paper: arXiv:2607.07435

Qwen2.5-Coder-14B-Instruct-Uncensored-Patched★ 5

gguf text-generation code coding-assistant qwen2.5-coder en

fable-coder-35B-A3B-GGUF★ 5

gguf code agentic moe qwen3.6 dappit

gemma-4-E4B-Agentic-Sol-Fable-Reasoning-GeminiCLI-mlx-4bit★ 5

mlx safetensors gemma4 4-bit quantized apple-silicon

granite-3.2-8b-lora-rag-citation-generation★ 5

peft safetensors text-generation conversational en arxiv:2409.11500

SciPhi-Self-RAG-Mistral-7B-32k-AWQ★ 5

transformers safetensors mistral text-generation arxiv:2310.11511 arxiv:2306.02707

Taiwan-LLM-7B-v2.0-chat-GGUF★ 5

transformers gguf text-generation zh arxiv:1910.09700 license:apache-2.0

Jackrong-llm-finetuning-guide★ 5

Learn LLM fine-tuning with an end-to-end guide for beginners and developers using Unsloth, LoRA, PEFT, and Google Colab

model-rush★ 5

沉浸式 AI 大模型训练体验。亲手搭建数据中心、采集数据、研发前沿技术、训练大模型,挑战基准测试最高分。

gguf-trainer★ 5

Train (from scratch) tiny GGUF language models on WebGPU

NVIDIA-Nemotron-Labs-Teacher-Chat★ 5

transformers safetensors nemotron_h text-generation nvidia pytorch

vikrant-OBLITERATUS★ 5

⚡ Advanced AI iteration framework featuring an 8-stage pipeline, automated fine-tuning, voice interaction, and security scanning.

Qwen2.5-Coder-7B-Instruct-Q8_0-GGUF★ 5

transformers gguf code codeqwen chat qwen

Qwen3.8-27B-DSpark-Agentic★ 5

safetensors qwen3 speculative-decoding dspark dflash draft-model

qwen3.8-9b-hermes-function-calling-v1★ 5

transformers safetensors qwen3_5 text-generation qwen3.5 function-calling

hrm-text-agent★ 5

transformers safetensors hrm_text text-generation function-calling tool-use

Qwen-0.8B-AgentJSON★ 5

safetensors qwen3_5_text tool-calling function-calling agent edge-ai

littlelearner-5b-chatty★ 5

transformers safetensors qwen3 text-generation littlelearner k5

K2-Chat-IMat-GGUF★ 5

gguf quantized GGUF imatrix quantization imat

qwen-coder-jailbreak★ 5

gguf qwen2.5 qwen2.5-coder code abliteration uncensored

python-assistant★ 5

transformers safetensors qwen2 text-generation llama-factory lora

HaleBlocks★ 5

Python library designed to make model experimentation seamless and fast. The goal was simple: treat every component (attention heads, MLPs, MoE layers) as a plug-and-play block so you can focus on the architecture, not the boilerplate.

Qwen3.8-27B-DSpark-Agentic★ 5

safetensors qwen3 speculative-decoding dspark dflash draft-model

Yi-1.5-34B-Chat-GGUF★ 5

transformers gguf mistral quantized 2-bit 3-bit

Qwen2.5-Coder-1.5B-Instruct-Q4_K_M-GGUF★ 5

transformers gguf code codeqwen chat qwen

Qwen3-Coder-Next-Uncensored-Heretic-GGUF★ 5

transformers gguf qwen3_next heretic uncensored decensored

CantoneseLLM-v2.0-30B-A3B-Thinking-Chat-Vector-Merged★ 5

transformers safetensors qwen3_moe text-generation cantonese hong-kong

tora-code-34b-v1.0-GGUF★ 5

transformers gguf llama code math text-generation

internlm2_5-20b-chat-GGUF★ 5

gguf text-generation base_model:internlm/internlm2_5-20b-chat base_model:quantized:internlm/internlm2_5-20b-chat license:other endpoints_compatible

andrewzh_Absolute_Zero_Reasoner-Coder-14b-GGUF★ 5

gguf text-generation base_model:andrewzh/Absolute_Zero_Reasoner-Coder-14b base_model:quantized:andrewzh/Absolute_Zero_Reasoner-Coder-14b endpoints_compatible re

agentic-rl-from-scratch★ 5

No GPU, no LLM — agentic RL from scratch in pure Python. 不用 GPU、不用 LLM,纯 Python 手搓明白 Agentic RL 训练闭环(trajectory / reward / loss mask / GRPO)

Josiefied-Qwen2.5-Coder-14B-Instruct-abliterated-v1★ 5

safetensors qwen2 chat GGUF text-generation conversational

retrograd★ 5

Run and Fine-tune GGUF models, with LoRA or full weights, from SFT to agentic GRPO

MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic★ 5

transformers safetensors llama text-generation minicpm minicpm5

Orion-9B-Agentic-CodeCore-Merge★ 5

transformers safetensors qwen3_5 image-text-to-text text-generation-inference pytorch

firefly-llama2-7b-chat★ 5

transformers pytorch llama text-generation text-generation-inference endpoints_compatible

Agent-Reflex-8B★ 5

transformers safetensors qwen3 text-generation agent tool-use

Qwen2.5-Coder-7B-Instruct-heretic★ 5

safetensors gguf qwen2 code heretic uncensored

GrandLine_LLM★ 5

从零构建类 Qwen 3 Dense架构 / Deepseek MoE架构大语言模型,全链路打通“预训练、SFT、CoT蒸馏、GRPO 对齐与评测闭环”的端到端大模型训练管线。

Lunar-Network★ 4

Solving openAI's game 'Lunar-Lander' with Deep Reinforcement Learning

erictransformer★ 4

Local fine-tuning, pre-training and RAG for LLMs

tsln-python★ 4

Time Series Lean Notation for python, it is designed to maximize the token efficiency of time-series data to LLMs

multiagent-ddpg★ 4

Multi-agent DDPG on ml-agents environment

BharatwASI★ 4

BharatwASI is an Artificial Super Intelligence (ASI) enabled chatbot, pioneering India's journey towards self-reliance in AI. Developed by Decima Technologies. This repository contains the source code, model training scripts, API implementation, and deployment instructions for BharatwASI. Join us in shaping the future of India's AI supremacy!

dataset-generator★ 4

🧠 DataForge — An intelligent LLM fine-tuning dataset generator that transforms raw prompts into structured ShareGPT-format training data through a multi-stage AI pipeline. Built with FastAPI + React/TypeScript, featuring real-time progress tracking via SSE, and FAISS-powered deduplication. Just prompt it, and watch your dataset build itself. ⚡

silicondev★ 4

Local LLM fine-tuning and chat for Apple Silicon

sollanaframework★ 4

Behavior-driven cognitive experimentation toolkit with BCE (Behavioral Consciousness Engine) regularization, telemetry, and plug-and-play integrators for language-model training and evaluation.

MolMem★ 4

[ACL 2026 Main] MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization

local-llm-tuner★ 4

Agentic harness for iteratively improving a local LLM's structured-output quality, scored against a frontier-model gold standard.

OpenAgora★ 4

Open-source rollout, verification, and trajectory plane for agentic reinforcement learning.

MXNET-Seq2Seq★ 4

Seq2Seq implemented by MXNET

Dataset-Creator-App★ 4

Create Datasets , FineTune Models , Test Models - All in one place. Everything simplified

starmap★ 4

An auto-updating AI Model Catalog - Single binary CLI, REST/SSE Server - SDKs - Golang Package.

k2-gallery★ 4

streamlit region:us

text-generator-gpt-neo★ 4

gradio region:us

EleutherAI-gpt-j-6B★ 4

gradio region:us

rinna-japanese-gpt-neox-3.6b-instruction-x★ 4

gradio region:us

GPT_train_on_LLaMa★ 4

gradio region:us

GPT-Fine-Tuning-Formatter★ 4

gradio region:us

gpt2-nepali★ 4

gradio region:us

Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF★ 4

transformers gguf qwen world-model agent environment-simulation

gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF★ 4

gguf gemma4 coding agentic terminal tool-use

Qwen-AgentWorld-35B-A3B★ 4

transformers safetensors qwen3_5_moe image-text-to-text qwen unsloth

Arcee-Agent-GGUF★ 4

gguf text-generation en de ar license:apache-2.0

Llama-3-Groq-8B-Tool-Use-GGUF★ 4

gguf facebook meta pytorch llama llama-3

Llama-3-Groq-70B-Tool-Use-GGUF★ 4

gguf quantized 2-bit 3-bit 4-bit 5-bit

Turkish-Llama-3-8B-function-calling★ 4

transformers safetensors llama text-generation text-generation-inference unsloth

Llama-2-7b-chat-hf-function-calling-v2-GGUF★ 4

transformers gguf mistral quantized 2-bit 3-bit

gemma-4-31B-it-qat-assistant-NVFP4-Blackwell★ 4

safetensors gemma4_assistant tensorizer modelopt nvidia fp4

Yi-1.5-9B-Chat-16K-abliterated★ 4

transformers safetensors llama text-generation llm long context

Xiangxin-2XL-Chat-1048k-Chinese-Llama3-70B★ 4

transformers safetensors llama text-generation conversational zh

SDAR-8B-Chat★ 4

transformers safetensors sdar text-generation conversational custom_code

maestrale-chat-v0.4-alpha-sft★ 4

transformers safetensors mistral text-generation sft it

Deepseek-LLM-7B-Chat-GGUF★ 4

transformers gguf llama text-generation base_model:deepseek-ai/deepseek-llm-7b-chat base_model:quantized:deepseek-ai/deepseek-llm-7b-chat

leo-hessianai-7B-chat-bilingual-GGUF★ 4

transformers gguf llama text-generation en de

llama-2-7b-chat-bnb-4bit★ 4

transformers safetensors llama text-generation unsloth llama-2

Yi-1.5-9B-Chat-GGUF★ 4

transformers gguf mistral quantized 2-bit 3-bit

Yi-1.5-34B-Chat-GGUF★ 4

transformers gguf llama text-generation base_model:01-ai/Yi-1.5-34B-Chat base_model:quantized:01-ai/Yi-1.5-34B-Chat

llama-2-13B-chat-limarp-v2-merged-GGUF★ 4

transformers gguf llama llama-2 text-generation en

leo-hessianai-7B-chat-GGUF★ 4

transformers gguf llama text-generation en de

kogpt2-emotion-chatbot★ 4

transformers pytorch gpt2 text-generation text-generation-inference endpoints_compatible

Qwen1.5-1.8B-Chat-AWQ★ 4

transformers safetensors qwen2 text-generation chat conversational

Qwen1.5-14B-Chat-GGUF★ 4

transformers gguf qwen2 text-generation chat en

Qwen3-Coder-30B-A3B-Instruct-gptq-4bit★ 4

transformers safetensors qwen3_moe text-generation qwen3 qwen

More in Agent frameworks & infrastructure