Agent frameworks & infrastructure

Models, fine-tuning & training

2,504 agents · most starred first

Models, fine-tuning & training, page 13 of 26

gpt-human-assistant★ 6

transformers pytorch safetensors gpt2 text-generation generated_from_trainer

llama-2-7b-chat★ 6

transformers safetensors llama text-generation unsloth llama2

internlm2-chat-7b-sft★ 6

transformers safetensors internlm2 text-generation conversational custom_code

maestrale-chat-v0.2-alpha-sft★ 6

transformers safetensors mistral text-generation sft it

Tower-Babel_Babel-9B-Chat-GGUF★ 6

gguf multilingual babel text-generation en zh

tinyllama-chat★ 6

transformers safetensors llama text-generation unsloth tinyllama

Llama3.1-8B-Chinese-Chat-GGUF★ 6

transformers gguf llama-factory orpo text-generation en

Bahasa-4b-chat★ 6

transformers safetensors qwen2 text-generation conversational id

Qwen2.5-Coder-0.5B-Instruct-4bit★ 6

transformers safetensors qwen2 text-generation code codeqwen

Qwen2.5-Coder-1.5B-Instruct★ 6

transformers safetensors qwen2 text-generation unsloth conversational

codegen-350M-nl★ 6

transformers pytorch codegen text-generation arxiv:2203.13474 license:bsd-3-clause

Qwen3-Coder-Next-AWQ-8bit★ 6

transformers safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next

code-autocomplete-gpt2-base★ 6

transformers pytorch safetensors gpt2 text-generation code

supergemma4-26b-abliterated-multimodal-nvfp4★ 6

transformers safetensors gemma4 image-text-to-text 26b 4-bit

gpt-oss-20b-hermes_agent-tool-finetune_gguf★ 6

gguf gpt-oss moe agent hermes-agent tool-use

nesso-0.4B-agentic★ 6

transformers safetensors llama text-generation small-language-model slm

glm-4-9b-chat-GGUF★ 6

gguf glm chatglm thudm text-generation zh

glm-4-9b-chat-IMat-GGUF★ 6

gguf glm chatglm thudm quantized GGUF

speechless-zephyr-code-functionary-7b★ 6

transformers safetensors gguf mistral text-generation en

Unsloth-Qwen3.6-27B-NVFP4-GGUF★ 6

gguf chain-of-thought nvfp4 qwen qwen3.6 quantized

Qwen2.5-Coder-0.5B-Instruct-GGUF★ 6

gguf code codeqwen chat qwen qwen-coder

deepseek-coder-6.7B-kexer-GGUF★ 6

gguf code text-generation dataset:JetBrains/KExercises base_model:JetBrains/deepseek-coder-6.7B-kexer base_model:quantized:JetBrains/deepseek-coder-6.7B-kexer

Qwen2.5-Coder-7B★ 6

transformers safetensors qwen2 text-generation unsloth code

deepseek-coder-1.3B-kexer-GGUF★ 6

gguf code text-generation dataset:JetBrains/KExercises base_model:JetBrains/deepseek-coder-1.3B-kexer base_model:quantized:JetBrains/deepseek-coder-1.3B-kexer

glm-4-9b-chat-1m-GGUF★ 6

gguf glm chatglm thudm text-generation zh

Jais-2-8B-Chat-GGUF★ 6

transformers gguf llama.cpp text-generation ar en

Qwen35B-Agent-R2-Abliterated-i1-GGUF★ 6

transformers gguf qwen moe mixture-of-experts agent

AceGPT-v2-8B-Chat★ 6

transformers safetensors llama text-generation ar zh

qwen27B-Agent-R2-abliterated-preview★ 6

transformers safetensors gguf qwen3_5_text text-generation qwen

Agents-A1-4B-F16-GGUF★ 6

transformers gguf vlm vision agentic text-generation

BananaMind-2-Nano-Chat★ 6

transformers safetensors bananamind2_nano text-generation causal-lm chat

Qwen2.5-Coder-14B-bnb-4bit★ 6

transformers safetensors qwen2 text-generation unsloth code

optiverse★ 6

A Python library for evolving code and algorithms using Large Language Models (LLMs)

KAT-Coder-V2.5-Dev-AWQ-INT4★ 6

transformers safetensors qwen3_5_moe image-text-to-text code agent

autosynth★ 6

Agentic synthetic-data generation framework inspired by Meta FAIR's Autodata / Agentic Self-Instruct.

MiniCPM5-1B-Agentic-Tooluse-v3-GGUF★ 6

gguf llama.cpp llama-cpp ollama lm-studio minicpm

MLewd-ReMM-L2-Chat-20B-Inverted★ 6

transformers safetensors llama text-generation not-for-all-audiences nsfw

LightRL★ 6

A lightweight, scalable RL post-training framework for agentic environments.

Qwen2.5-Coder-3B-Instruct★ 6

litert-lm litertlm qwen Qwen2.5 text-generation en

Qwen2.5-Coder-1.5B★ 6

transformers safetensors qwen2 text-generation unsloth en

Qwen2.5-Coder-0.5B-Instruct★ 6

transformers.js onnx qwen2 text-generation conversational base_model:Qwen/Qwen2.5-Coder-0.5B-Instruct

Qwen-35B-A3B-SignOfFour-Coder★ 6

transformers safetensors qwen3_5_moe text-generation merge ties

jais-family-1p3b-chat★ 6

safetensors jais Arabic English LLM Decoder

polylm-chat-13b★ 6

transformers pytorch gpt2 text-generation arxiv:2307.06018 license:apache-2.0

wald-4b★ 6

Wald-Q4B: open-weight 4B decision model. Calibrated probability for every option, Jev-compatible /v1/systemone API, self-hosted. Weights on Hugging Face.

Qwen3.5-4B-Python-Coder-GGUF★ 6

gguf qwen qwen3.5 code python text-generation

Qwen3.8-27B-Coder390-oQ4e-MTP-Text★ 6

mlx safetensors qwen3_5 omlx 4-bit mtp

Tals-coder-flash-02★ 6

gguf ternary speculative-decoding mtp vision multimodal

afterlife★ 6

Afterlife lets you, an agent running on a local model, nominate experiences from your activity for training into a small LoRA adapter to isekai your future self.

llm-agents-tora-70b-v1.0★ 6

gradio region:us

qwen25-coder-3b-uncensored★ 6

transformers gguf qwen2 text-generation code abliterated

osmosis-sdk-python★ 5

Python SDK for Osmosis AI training workflows. Supports two training modes with shared tooling for testing and evaluation.

NLP-LLM★ 5
AI-Planet-LLM-Bootcamp-Challenge★ 5

An LLM challenge to (i) fine-tune pre-trained HuggingFace transformer model to build a Code Generation language model, and (ii) build a retrieval-augmented generation (RAG) application using LangChain

Minimax-Multi-Agent-Deep-Deterministic-Policy-Gradient★ 5

A general pytorch implementation of the Minimax Multi-Agent Deep Deterministic Policy Gradient (M3DDPG) algorithm used for multiagent reinforcement learning.

llm-friend-bot★ 5

This project seeks to fine-tune the GPT-2.5 model with a personal touch. By training it on personal Telegram chats, we aim to capture the essence of individualized writing styles. To spice things up, we've also fed the model a sprinkle of anecdotes and a dash of math tasks.

seq2seq-chatbot★ 5

An attention-based seq2seq neural network chatbot with PyTorch, trained on Microsoft's MetaLWOz dataset.

multilayer_bidirectional_chatbot★ 5

A multi-layer bidirectional seq-2-seq chatbot with bahdanau attention.

chatbot_pytorch★ 5

对于pytorch官网chatbot的教程做了模块化的处理,包含大量的注释

HaloBlocks★ 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.

chatbot★ 5

pytorch前馈网络分类预测chatbot

autorlx★ 5

Interactive Platform for Automated Reinforcement Learning on the Web

LLM-Model-Distillation-for-Text-Classification-Models-GUI★ 5

GUI application that performs knowledge distillation from OpenAI models to smaller Hugging Face models for efficient text classification tasks.

PaliGemma-FineTuning★ 5

PaliGemma FineTuning

CartPole-v0_DeepRL★ 5

OpenAI CartPole-v0 DeepRL-based solutions (DQN, DuelingDQN, D3QN)

Reinforce_Adventure★ 5

This Repository contains my implementation of popular algorithms on popular environments.

Rise-of-Transfer-Learning★ 5

you will find brief code implementations of some of the latest developments in AI, including Stable Diffusion, Whisper, YOLO and HuggigFace Transformers

distil★ 5

The lazy engineer's salvation for prompt versioning and fine-tuning. We handle the boring stuff, you take the credit.

Chatbot-Free-Datasets★ 5
DeltaLoop★ 5

Continuous fine-tuning layer that converts AI agent logs into LoRA adapters.

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)

light-tuning★ 5

🤖 CLI to fine-tune GPT-3.5 Turbo models rapidly. 💬

open_qwen★ 5

Build and deploy large language models with Open Qwen, a PyTorch-based framework for efficient, flexible AI development and research.

llmc_1558M★ 5

gradio region:us

Generate-Mergkit-For-Upscale-LLM★ 5

static region:us

Hebrew-GPT-Neo-Small★ 5

streamlit region:us

vicgalle_alpaca-gpt4★ 5

static region:us

SuperQwen-AgentWorld-35B-A3B-abliterated-nvf4★ 5

mlx safetensors qwen3_5_moe qwen-agentworld abliterated nvfp4

Llama3.1-vodka★ 5

transformers safetensors llama text-generation llama-3 uncensored

LFM2.5-1.2B-Nova-Function-Calling★ 5

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

deepseek-coder-6.7b-instruct-function-calling-v2★ 5

transformers safetensors llama text-generation deepseek deepseek coder

zephyr-7b-beta-function-calling-v2★ 5

transformers safetensors gguf mistral text-generation facebook

Yi-34B-200K-Llamafied-function-calling-v2★ 5

transformers safetensors llama text-generation yi function calling

Yi-34B-200K-Llamafied-chat-SFT-function-calling-v3★ 5

transformers safetensors llama text-generation yi long context

SUS-Chat-34B-function-calling-v3★ 5

transformers safetensors llama text-generation yi long context

phi-3-bangla-instruct★ 5

transformers safetensors mistral text-generation conversational bn

qwen3-1.7b-lamini-qlora-instruction-tuned★ 5

transformers safetensors qwen3 text-generation instruction-tuning sft

TinyLlama-1.1B-Chat-v0.3-AWQ★ 5

transformers safetensors llama text-generation en dataset:cerebras/SlimPajama-627B

tinyllama-chat-bnb-4bit★ 5

transformers safetensors llama text-generation unsloth tinyllama

ChatTime-1-7B-Chat★ 5

transformers safetensors llama text-generation time-series pretrained-model

buddhi-128k-chat-7b-GGUF★ 5

gguf text-generation license:apache-2.0 endpoints_compatible region:us conversational

glm-4-9b-chat-abliterated-GGUF★ 5

transformers gguf glm chatglm thudm chat

llama-3-neural-chat-v2.2-8B-GGUF★ 5

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

dolphin-2_6-phi-2_oasst2_chatML_V2-GGUF★ 5

gguf ggml quantized q2_k q3_k_m q4_k_m

Qwen3-0.6B-accuracy-recovery-lora★ 5

peft safetensors ellora lora quantization accuracy-recovery

Kimi-K2.7-Code-4bit★ 5

mlx safetensors kimi_k25 text-generation conversational custom_code

Kimi-K2.7-Code-mlx-DQ3_K_M-q8★ 5

mlx safetensors kimi_k25 feature-extraction transformers text-generation

qwen2.5-coder-14b-bitnet-1.58b★ 5

safetensors gguf qwen2 bitnet quantization ternary

Qwen2.5-Coder-7B-Instruct-GPTQ-Int8★ 5

transformers safetensors qwen2 text-generation code codeqwen

Qwen2.5-Coder-3B★ 5

transformers safetensors qwen2 text-generation unsloth code

More in Agent frameworks & infrastructure