Agent frameworks & infrastructure

Models, fine-tuning & training

2,504 agents · most starred first

Models, fine-tuning & training, page 11 of 26

Qwen2.5-Coder-7B-GGUF★ 10

transformers gguf code qwen qwen-coder codeqwen

Post-Training-Challenge★ 10

gradio region:us

Qwen2.5-Coder-14B-Instruct-Uncensored-Q4_K_M-GGUF★ 10

transformers gguf 14b 4-bit Q4_K_M coder

paza-Phi-4-multimodal-instruct★ 10

transformers safetensors phi4mm text-generation nlp code

Qwen2.5-Coder-1.5B-Instruct-AWQ★ 10

transformers safetensors qwen2 text-generation code codeqwen

Qwen1.5-4B-Chat-AWQ★ 10

transformers safetensors qwen2 text-generation chat conversational

gemma-4-E4B-Agentic-Sol-Fable-Reasoning-GeminiCLI-GGUF★ 10

gguf gemma4 quantized reasoning chain-of-thought sol

NeuroBranch★ 10

Compose neural architectures as typed, executable graph cards with two-way PyTorch sync, step-by-step local execution, and a constrained AI graph planner.

jais-adapted-7b-chat★ 10

safetensors llama Arabic English LLM Decoder

BananaMind-2-Pro-Preview-Chat★ 10

transformers safetensors bananamind2_pro text-generation causal-lm chat

Qwen3.8-Flash-Next-MTP-ROCmFP4-FAST-GGUF★ 10

gguf mtp speculative-decoding rocmfp4 vulkan strix-halo

jais-family-13b-chat★ 10

safetensors jais Arabic English LLM Decoder

openthaigpt-1.0.0-beta-7b-chat-ckpt-hf★ 10

transformers pytorch llama text-generation openthaigpt th

dream-rsi-sdk★ 10

Independent, unofficial Dream-RSI-inspired Python SDK. Alpha: model-agnostic adapters, recorded-tree replay and policy search. Not affiliated with Google.

llm-agents_tora-code-7b-v1.0-GGUF★ 10

transformers gguf code math TensorBlock GGUF

tiny-llm★ 10

A small LLM built from scratch in PyTorch. Loads GPT-2, Llama (SmolLM2), Qwen2.5 and Pythia weights with outputs identical to Hugging Face. LoRA fine-tuning, KV cache, Kaggle/Colab notebook and a Streamlit chatbot.

Open-EmbeddingGemma★ 10

Implementation of EmbeddingGemma 2, Google DeepMind's 740M parameter multimodal embedding model, in Pytorch

SynthToT★ 9

SynthToT: Generate synthetic dataset for your training dataset through deliberate problem-solving et al S Yao, 2023.

OmniByteGPT★ 9

An implementation of an all-new foundation model architecture that trains on byte sequences from multiple modalities to handle omni-modal generation of text, video, images and more.

embedding-hallucinations★ 9

This repo shows how foundational model hallucinates and how we can fix such hallucinations using fine-tuning them

QLoRA-Fine-tuning-for-Film-Character-Styled-Responses-from-LLM★ 9

Code for fine-tuning Llama2 LLM with custom text dataset to produce film character styled responses

Jade_T5★ 9

Conversational T5 model, finetuned for long-context conversational tasks

gpt3datagen★ 9

GPT3DataGen is a python package that generates fake data for fine-tuning openai models

scaling-laws-for-language-transfer★ 9

code for Scaling Laws for Language Transfer Learning

rag-forge★ 9

Framework for fine-tuning LLMs on retrieval-augmented generation tasks

miniGPT★ 9

Building GPT from scratch & training on a Single Consumer GPU

rag-model-training★ 9

Training code for advanced RAG techniques - Adaptive-RAG, Corrective RAG, RQ-RAG, Self-RAG, Agentic RAG, and ReZero. Reproduces paper methodologies to fine-tune LLMs via SFT and GRPO for adaptive retrieval, corrective evaluation, query refinement, self-reflection, and agentic search behaviors.

SPROUT★ 9

Official repository for SPROUT - ICML 2026

OpenCoder-1.5B-Instruct★ 9

gradio region:us

lora-cerebras-gpt2.7b-alpaca-shortprompt★ 9

gradio region:us

Athene-V2-Agent-GGUF★ 9

gguf RLHF Nexusflow Athene Function Calling Agent

dolphin-2.6-mistral-7b-dpo-laser-function-calling★ 9

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

Mistral-7B-Instruct-v0.2-Function-Calling★ 9

transformers safetensors mistral text-generation function-call conversational

Mistral-7B-Instruct-v0.1-function-calling-v3★ 9

transformers safetensors mistral text-generation facebook meta

Yi-1.5-6B-Chat-GGUF★ 9

transformers gguf mistral quantized 2-bit 3-bit

maestrale-chat-v0.4-beta★ 9

transformers safetensors mistral text-generation sft it

PLLuM-12B-chat-2412★ 9

transformers safetensors mistral text-generation conversational pl

openthaigpt-1.0.0-beta-13B-chat-GGUF★ 9

transformers gguf llama openthaigpt text-generation th

XVERSE-7B-Chat★ 9

transformers pytorch xverse text-generation custom_code arxiv:2009.03300

TinyLlama-1.1B-Chat-v0.2-gguf★ 9

gguf text-generation en dataset:cerebras/SlimPajama-627B dataset:bigcode/starcoderdata dataset:OpenAssistant/oasst_top1_2023-08-25

Yi-1.5-34B-Chat-GGUF★ 9

gguf text-generation base_model:01-ai/Yi-1.5-34B-Chat base_model:quantized:01-ai/Yi-1.5-34B-Chat license:apache-2.0 endpoints_compatible

PLLuM-12B-nc-chat-2412★ 9

transformers safetensors mistral text-generation conversational pl

Qwen3-4b-toolcall-gguf-llamacpp-codex★ 9

safetensors gguf qwen3 function-calling tool-calling codex

Qwen1.5-0.5B-Chat★ 9

transformers.js onnx qwen2 text-generation conversational base_model:Qwen/Qwen1.5-0.5B-Chat

glm-edge-4b-chat-gguf★ 9

gguf glm edge text-generation zh en

gemma-4-E2B-it-assistant-GGUF★ 9

gguf atomic-chat gemma gemma4 google llama.cpp

Qwen3-Coder-30B-A3B-Instruct-AWQ★ 9

transformers safetensors qwen3_moe text-generation conversational arxiv:2505.09388

Yi-6B-Chat-8bits★ 9

transformers safetensors llama text-generation conversational arxiv:2403.04652

Qwen3-0.6B-Code-Expert★ 9

transformers safetensors qwen3 text-generation unsloth trl

Llama-3-11.5B-Instruct-Coder-v2-GGUF★ 9

transformers gguf text-generation-inference unsloth llama trl

jais-family-6p7b-chat★ 9

safetensors jais Arabic English LLM Decoder

Dream-Coder-v0-Base-7B★ 9

transformers safetensors Dream feature-extraction text-generation conversational

codellama-7b-bnb-4bit★ 9

transformers safetensors llama text-generation unsloth codellama

Improved-Chat-Template-for-Qwen-3.x★ 9

qwen3_5_moe chat-template jinja qwen qwen2.5 qwen3

Harbor-RL★ 9

An end-to-end framework for Agentic Reinforcement Learning.

Instinct-Python-Coder-Gemma4-12B-Qwen3.8-27B★ 9

gguf llama.cpp gemma python code reasoning

Aztec-Coder-4B★ 9

transformers safetensors qwen3_5_text text-generation agentic-coding reasoning

flan-t5-fine-tune★ 8

Flan-t5 model fine tune LoRA and Langchain

JaxTransformer★ 8

This repository demonstrates how to build a Decoder-Only Transformer with Multi-Query Attention in JAX.

DPO-MCTS-ToT-Training★ 8

This module implements a post-training mechanism that allows a language model to explore various reasoning branches (chain-of-thoughts) using a Monte Carlo Tree Search (MCTS) framework. It selects the branch with the best answer using a cosine similarity evaluator that compares the candidate answer to a known correct answer.

open-domain-chatbot★ 8

[WIP] A chatbot based on the paper "A nerual conversational model" from Google, built with TensorFlow

baseline_for_chatbot-mxnet★ 8

this repo use mxnet to implement baselines for retrieval chatbot

EmbraceBERT★ 8

Attentively Embracing Noise for Robust Latent Representation in BERT (COLING 2020)

Nous★ 8

A fully configurable, from-scratch GPT-style experimental model and platform with a GUI for training and inference.

fine-tune-forge★ 8

JSONL generator designed for models like Google PaLM 2 and OpenAI GPT-3.5

openai-finetuning-model-creator★ 8

This tool is designed for people who want to customize their own AI models without dealing with complicated code. Everything you need can be done right from this user-friendly web interface.

DART★ 8

DART (Diffusion-Autoregressive Recursive Transformer) is a novel hybrid architecture that combines diffusion-based and autoregressive approaches for text generation.

Pong-v4_DeepRL★ 8

Atari OpenAI Pong-v4 DeepRL-based solutions (DQN, DuelingDQN, D3QN)

fine-tuning-embeddings-template★ 8

This repo is a template to fine-tune embedding models using sentencetransformers based on different on configuration

gai-project★ 8

Train expert conversational role-play LLMs with synthetic data

LLM-FineTuning-Notebook-Generator★ 8

gradio region:us

gpt2-indonesian★ 8

streamlit region:us

Agents-A1-Q4_K_M-GGUF★ 8

gguf MoE agent tool-use long-horizon text-generation

Tiny-Agent-a-1.5B★ 8

transformers safetensors gguf qwen2 text-generation code

Athene-V2-Agent-GGUF★ 8

gguf RLHF Nexusflow Athene Function Calling Agent

Fabliq-8B-Agent★ 8

transformers safetensors lfm2_moe text-generation lfm liquid-ai

Arch-Agent-3B★ 8

transformers safetensors qwen2 text-generation conversational en

ABEJA-Qwen3-14B-Agentic-256k-v0.1★ 8

transformers safetensors qwen3 text-generation conversational ja

CodeLlama-function-calling-6320-7b-Instruct-hf★ 8

transformers pytorch llama text-generation dataset:rizerphe/glaive-function-calling-v2-llama dataset:rizerphe/sharegpt-hyperfiltered-3k-llama

Llama-2-70b-AQLM-2Bit-QLoRA-function-calling★ 8

peft safetensors llama-factory lora generated_from_trainer text-generation

deepseek-llm-67b-chat-function-calling-v3★ 8

transformers safetensors llama text-generation function-calling function calling

Llama-2-13B-german-assistant-v2★ 8

transformers pytorch safetensors llama text-generation en

Yi-1.5-9B-Chat-GGUF★ 8

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

jais-adapted-7b-chat★ 8

safetensors llama Arabic English LLM Decoder

TinyLlama-1.1B-Chat-v1.0★ 8

transformers.js onnx llama text-generation conversational base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0

Yi-1.5-9B-Chat-GGUF★ 8

transformers gguf llama text-generation base_model:01-ai/Yi-1.5-9B-Chat base_model:quantized:01-ai/Yi-1.5-9B-Chat

internlm2_5-20b-chat-GGUF★ 8

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

manticore-13b-chat-pyg-GGUF★ 8

transformers gguf llama text-generation en dataset:anon8231489123/ShareGPT_Vicuna_unfiltered

Tiny-Hinglish-Chat-21M★ 8

transformers pytorch tflite onnx safetensors gpt2

Qwen3-Coder-480B-A35B-Instruct-AWQ★ 8

transformers safetensors qwen3_moe text-generation Qwen3 AWQ

Qwen-AgentWorld-35B-A3B-NVFP4★ 8

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

openPangu-7B-Diffusion-DeepDiver★ 8

safetensors PanguEmbedded text-generation conversational custom_code arxiv:2602.07451

SDAR-1.7B-Chat★ 8

transformers safetensors sdar text-generation conversational custom_code

glm-edge-1.5b-chat-gguf★ 8

gguf glm edge text-generation zh en

LLMFineTuningDeployment★ 8

streamlit region:us

Qwen-AgentWorld-35B-A3B-MTP-APEX-GGUF★ 8

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

MiniCPM5-1B-Agentic-Tooluse-Merged-FP16★ 8

transformers safetensors llama text-generation minicpm minicpm5

granite-34b-code-instruct-GGUF★ 8

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

Trinity-2-Codestral-22B-GGUF★ 8

gguf generated_from_trainer text-generation base_model:migtissera/Trinity-2-Codestral-22B base_model:quantized:migtissera/Trinity-2-Codestral-22B license:other

Instinct-Python-Coder-Gemma4-12B-KimiK3★ 8

gguf llama.cpp gemma python code reasoning

More in Agent frameworks & infrastructure