Agent frameworks & infrastructure

Models, fine-tuning & training

2,504 agents ยท most starred first

Models, fine-tuning & training, page 9 of 26

llama-3-8B-Instruct-function-calling-v0.2โ˜… 21

transformers safetensors llama text-generation conversational en

openchat_3.5-function-calling-v3โ˜… 21

transformers safetensors mistral text-generation openchat C-RLFT

MobileLLaMA-1.4B-Chatโ˜… 21

transformers pytorch llama text-generation dataset:Aeala/ShareGPT_Vicuna_unfiltered arxiv:2312.16886

codegen-2B-monoโ˜… 21

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

agentlm-13bโ˜… 21

transformers safetensors llama text-generation dataset:THUDM/AgentInstruct arxiv:2310.12823

gemma-4-31B-it-assistant-bf16โ˜… 21

mlx safetensors gemma4_assistant speculative-decoding mtp gemma

qwen2.5-coder-3b-claude_opus_4.6-distilledโ˜… 21

safetensors gguf qwen2 qwen2.5 qwen2.5-coder unsloth

gemma-4-E4B-it-qat-q4_0-unquantized-assistantโ˜… 21

transformers safetensors gemma4_assistant text-generation any-to-any arxiv:2607.02770

Qwen2.5-Coder-14B-Instruct-4bitโ˜… 21

transformers safetensors qwen2 text-generation code codeqwen

Qwen2.5-Coder-3B-Q8_0-GGUFโ˜… 21

transformers gguf code qwen qwen-coder codeqwen

Fabliq-8B-Agent-Reasoningโ˜… 21

transformers safetensors lfm2_moe text-generation lfm liquid-ai

Yi-6B-Chat-4bitsโ˜… 21

transformers safetensors llama text-generation conversational arxiv:2403.04652

GLM-5.3-Flash-REAP144-Coder-GGUFโ˜… 21

gguf moe expert-pruning reap code agentic

qwen3.8-flash-coder-44gb-selective-int8โ˜… 21

transformers safetensors qwen4_exp_text text-generation moe qwen

HybridAgent-14B-Agenticโ˜… 21

safetensors qwen3 hybrid-reasoning latent-reasoning agent tool-use

go-tiktokenโ˜… 20

โœ‚๏ธ OpenAI's tiktoken tokenizer written in Go

Arch-Agent-32Bโ˜… 20

transformers safetensors qwen2 text-generation conversational en

Llama-2-70b-chat-hfโ˜… 20

transformers pytorch safetensors llama text-generation facebook

Nile-Chat-4Bโ˜… 20

transformers safetensors gemma3_text text-generation conversational arz

Llama-160M-Chat-v1โ˜… 20

transformers safetensors llama text-generation conversational en

leo-hessianai-7b-chatโ˜… 20

transformers pytorch llama text-generation conversational custom_code

pyTPGโ˜… 20

pyTPG โ€” A modern, modular Python framework for Tangled Program Graphs. Install with `pip install pytpg`.

CodeLlama-34b-hfโ˜… 20

transformers pytorch safetensors llama text-generation facebook

Qwen3.5-27b-Sushi-Coder-RL-GGUFโ˜… 20

gguf llama.cpp qwen3_5 code rl atropos

h2ogpt-4096-llama2-70b-chatโ˜… 20

transformers pytorch safetensors llama text-generation facebook

huggingface-transformer-chatbotsโ˜… 19

A collection of simple transformer based chatbots.

Sailor2-8B-Chatโ˜… 19

transformers safetensors qwen2 text-generation multilingual sea

SuperQwen-AgentWorld-35B-A3B-abliteratedโ˜… 19

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

Huihui-Qwen-AgentWorld-35B-A3B-abliteratedโ˜… 19

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

Qwen1.5-0.5B-Chat-GPTQ-Int4โ˜… 19

transformers safetensors qwen2 text-generation chat conversational

tora-7b-v1.0โ˜… 19

transformers pytorch llama text-generation code math

Agents-A1-Uncensored-MTP-APEX-GGUFโ˜… 19

transformers gguf qwen3_5_moe qwen3_5 reasoning agentic

ModelAdaptationBookโ˜… 19

Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA, full SFT, distillation, and DPO/RLHF alignment.

CodeLlama-34b-Instruct-hfโ˜… 19

transformers pytorch safetensors llama text-generation facebook

GLM-4.7-Flash-Coderโ˜… 19

transformers safetensors glm4_moe_lite text-generation conversational dataset:whitecircle/swe-rebench-v2-glm-5.1-pi-agent-successful-traces

CodeGPT-small-java-adaptedGPT2โ˜… 19

transformers pytorch tf jax gpt2 text-generation

reinforcement-learning-agentsโ˜… 18

a collection of advanced reinforcement learning (rl) agents and implementations, including dqn, actor-critic, ppo, dpo, and more. provides reference code, algorithmic insights, and setups for research, experimentation, and benchmarking of state-of-the-art rl methods.

intent-detection-using-XLM-Robertaโ˜… 18

This repository is a comprehensive project that leverages the XLM-Roberta model for intent detection. This repository is a valuable resource for developers looking to build and fine-tune intent detection models based on state-of-the-art techniques.

Seq2Seq-chatbotโ˜… 18

TensorFlow Implementation of Twitter Chatbot

MXNET-SMNโ˜… 18

Sequential Matching Network implemented by MXNET

HDNOโ˜… 18

This is the source code for HDNO: a hierarchical model for task-oriented dialogue system.

JSONLgeneratorโ˜… 18

an easy way to create JSONL files for fine-tuning openai models.

polka-1.1b-chatโ˜… 18

transformers safetensors llama text-generation generated_from_trainer conversational

Qwen1.5-32B-Chat-AWQโ˜… 18

transformers safetensors qwen2 text-generation chat conversational

openthaigpt-1.0.0-7b-chatโ˜… 18

transformers safetensors gguf llama text-generation openthaigpt

llama-3-neural-chat-v1-8bโ˜… 18

transformers safetensors llama text-generation conversational dataset:mlabonne/orpo-dpo-mix-40k

Qwopus3.5-4B-Coderโ˜… 18

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

Olmo-3-7B-RL-Zero-Codeโ˜… 18

transformers safetensors olmo3 text-generation conversational en

Agents-A1-GGUFโ˜… 18

llama.cpp gguf quantized llama-cpp qwen3.5-moe mixture-of-experts

MiniCPM5-1B-Agent-GGUFโ˜… 18

transformers gguf agentic code tool-use agent

Qwen2.5-Coder-1.5B-Instruct-GGUFโ˜… 18

transformers gguf code codeqwen chat qwen

tora-13b-v1.0โ˜… 18

transformers pytorch llama text-generation code math

Huihui-gemma-4-12B-agentic-fable5-abliteratedโ˜… 18

transformers safetensors gemma4_unified image-text-to-text abliterated uncensored

Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUFโ˜… 18

gguf dflash2 speculative-decoding draft-model rocmfp4 vulkan

Fabliq-8B-Agent-FromBase-Reasoningโ˜… 18

transformers safetensors lfm2_moe text-generation lfm liquid-ai

Chatbot-with-TensorFlow-and-Kerasโ˜… 17

Chatbot using Seq2Seq model and Attention

opentrainโ˜… 17

๐Ÿš‚ Fine-tune OpenAI models for text classification, question answering, and more

deeprlโ˜… 17

A flexible and extensible reinforcement learning library for Python, designed for both beginners and researchers.

ben-decentralized-chatbotโ˜… 17

YC Hackathon 2018 Winner Project. BEN: A decentralized chatbot that uses federated learning.

Qwen2.5-Coder-14B-Instruct-abliteratedโ˜… 17

transformers safetensors qwen2 text-generation code codeqwen

NELLAโ˜… 17

๋ฌธ์„œ๋งŒ ์ฃผ๋ฉด ๋ฐ์ดํ„ฐ ์ƒ์„ฑยทํ•™์Šตยทํ‰๊ฐ€๊นŒ์ง€ ์•Œ์•„์„œ ๋„๋ฉ”์ธ LLM์„ ๋งŒ๋“ค์–ด์ฃผ๋Š” Agentic LLMOps ์—์ด์ „ํŠธ โ€” ์ž์—ฐ์–ด ์ง€์‹œ + Human-in-the-Loop, ๋กœ์ปฌ ๊ตฌ์ถ•. Chat-driven LLMOps agent that builds domain-specific LLMs from your documents.

RLZeroโ˜… 16

A clean and easy implementation of MuZero, AlphaZero and Self-Play reinforcement learning algorithms for any game.

chatbot-khanโ˜… 16

chatbot implementation on custom dataset from scratch, pytorch

Doppelgangerโ˜… 16

Fine-tune a local LLM on your own chat history to mimic how you write โ€” an AI doppelganger / digital-twin toolkit built on LLaMA-Factory (LoRA SFT).

Llama-2-13B-German-Assistant-v4-GPTQโ˜… 16

transformers safetensors llama text-generation en de

LLaMAntino-2-chat-13b-hf-UltraChat-ITAโ˜… 16

transformers pytorch safetensors llama text-generation text-generation-inference

Sailor2-1B-Chatโ˜… 16

transformers safetensors qwen2 text-generation multilingual sea

Vistral-7B-Chat-ggufโ˜… 16

gguf vistral mistral pytorch uonlp Viet-Mistral

SeaLLMs-v3-1.5B-Chatโ˜… 16

transformers safetensors qwen2 text-generation sea multilingual

vinallama-2.7b-chatโ˜… 16

transformers pytorch llama text-generation vi arxiv:2312.11011

EvolveXโ˜… 16

EvolveX is a research framework for principled agent self-improvement. It evolves prompts, skills, and agent code under frozen evaluators and declared mutation boundaries, recording verifiable lineage โ€” scores, artifacts, and Git-tagged generations, so every improvement is reproducible and auditable.

Qwen-7B-Chat-Int8โ˜… 16

transformers safetensors qwen text-generation custom_code zh

flaxrlโ˜… 16

RL and MARL with Flax NNX

ProgramGymโ˜… 16

Scaling Training Environments for Long-Horizon Program Reproduction Agents

HybridAgent-8B-Agenticโ˜… 16

safetensors qwen3 hybrid-reasoning latent-reasoning agent tool-use

LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3-GGUFโ˜… 16

hermes gguf duo-neural g-tap tap-dpq lfm2

dragonfarmโ˜… 16

Raise your own dragon: fine-tune a language model on your own documents, from R. Writes the training data, trains on your laptop, RAG built in.

SUS-Chat-34B-GGUFโ˜… 15

transformers gguf yi text-generation base_model:SUSTech/SUS-Chat-34B base_model:quantized:SUSTech/SUS-Chat-34B

AceGPT-7B-chatโ˜… 15

transformers pytorch llama text-generation ar arxiv:2309.12053

Nile-Chat-12Bโ˜… 15

transformers safetensors gemma3_text text-generation conversational arz

Qwen3-Coder-Next-DFlashโ˜… 15

transformers safetensors qwen3 feature-extraction dflash speculative-decoding

Qwen-AgentWorld-35B-A3B-MTP-Uncensored-APEX-GGUFโ˜… 15

transformers gguf qwen3_5_moe qwen-agentworld world-model agentic-environment-simulation

veriloop-coder-e1-ggufโ˜… 15

transformers gguf veriloop veriloop-coder code coding-agent

Llama-2-Coder-7B-GGUFโ˜… 15

transformers gguf llama generated_from_trainer code coding

Replete-Coder-Llama3-8B-GGUFโ˜… 15

transformers gguf text-generation-inference unsloth llama text-generation

local-code-tutorโ˜… 15

Fine-tune Qwen2.5-Coder-7B for free (QLoRA on Kaggle T4) and run a local coding agent that runs your code instead of guessing โ€” 8 GB Mac, llama.cpp, LoRA weight analysis with charts

ruvllmโ˜… 15

Governed neural weight editing and coding model adaptation. Native Rust patches, exact rollback, LoRA, Claude Code routing, and reproducible benchmarks.

llmsharp-tokenizersโ˜… 14

BPE Tokenizer implementations in C# for Anthropic, OpenAI LLM offerings

local-lora-cookbookโ˜… 14

Fine-tune a local LLM on your own app's data in 15 minutes. Runs entirely on-device, zero cloud after training. Apple Silicon + CUDA.

GPT-J-6Bโ˜… 14

gradio region:us

Agents-A1-F16-GGUFโ˜… 14

gguf moe vlm vision agentic text-generation

Phi-3-mini-128k-instruct-function-callingโ˜… 14

transformers safetensors phi3 text-generation nlp code

TinyLlama-1.1B-Chat-v1.0-GPTQโ˜… 14

transformers safetensors llama text-generation conversational en

glm-4-9b-chat-1m-hfโ˜… 14

transformers safetensors glm text-generation chatglm conversational

Trendyol-LLM-7b-chat-v0.1-GGUFโ˜… 14

transformers gguf llama text-generation trendyol llama-2

DeepSeek-Coder-V2-Lite-Instruct-FP8โ˜… 14

transformers safetensors deepseek_v2 text-generation fp8 vllm

granite-20b-code-base-8kโ˜… 14

transformers safetensors gpt_bigcode text-generation code granite

glm-4-9b-chat-abliterated-GGUFโ˜… 14

transformers gguf glm chatglm thudm chat

Qwen1.5-4B-Chat-GPTQ-Int4โ˜… 14

transformers safetensors qwen2 text-generation chat conversational

glm-4-9b-chat-abliteratedโ˜… 14

transformers safetensors chatglm glm thudm chat

More in Agent frameworks & infrastructure