Agent frameworks & infrastructure

Models, fine-tuning & training

2,504 agents · most starred first

Models, fine-tuning & training, page 12 of 26

SKILLER★ 8

Official implementation of SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models.

GGUF.chatgpt-gpt-gpt5.1-thinking★ 8

gguf TeichAI qwen3 unsloth text-generation en

qwen2.5-coder-32b-bitnet-1.58b★ 8

safetensors gguf qwen2 bitnet quantization ternary

micro-tiny-gpt-from-scratch★ 8

This is our micro-tiny GPT model (😁 we are still learning), built from scratch and inspired by the innovative approaches of Hugging Face Transformers and OpenAI architectures. Developed during our internship at 3D Smart Factory, this model showcases our committed efforts to create an advanced AI solution.

genpark-reinforcement-fine-tuning-trajectory-buffer-skill★ 8

GenPark AI Agent Skill - Prioritized experience replay buffer for agent reinforcement fine-tuning (RFT / GRPO) with advantage estimation and importance sampling weights.

genpark-knowledge-distillation-teacher-student-tracker-skill★ 8

GenPark AI Agent Skill - Knowledge distillation teacher-student loss engine with temperature-scaled Kullback-Leibler divergence for continual model compression and capability preservation.

genpark-pairwise-preference-dpo-loss-tracker-skill★ 8

GenPark AI Agent Skill - Direct Preference Optimization (DPO) implicit reward calculation, reference policy log-ratio tracking, and pairwise preference loss evaluation.

genpark-synaptic-intelligence-path-integral-skill★ 8

GenPark AI Agent Skill - Synaptic Intelligence (SI) online path integral engine accumulating parameter trajectory contributions to protect vital synaptic pathways across tasks.

genpark-gradient-episodic-memory-gem-projector-skill★ 8

GenPark AI Agent Skill - Gradient Episodic Memory (GEM / A-GEM) projection engine constraining parameter updates to prevent interference with past task gradients.

genpark-elastic-weight-consolidation-fisher-reg-skill★ 8

GenPark AI Agent Skill - Elastic Weight Consolidation (EWC) engine calculating Fisher Information Matrix diagonal penalties to prevent catastrophic forgetting during sequential task learning.

genpark-kahneman-tversky-kto-utility-loss-skill★ 8

GenPark AI Agent Skill - Kahneman-Tversky Optimization (KTO) loss evaluator aligning agents directly on unpaired binary feedback (thumbs-up / thumbs-down) using prospect theory loss aversion.

KAT-Coder-V2.5-Dev-35B-A3B-MTP-ABLITERATED-GGUF★ 8

gguf llama.cpp qwen3_5_moe kat-coder kat-coder-v2.5 qwen3.5

Qwen2.5-Coder-3B-Uncensored★ 8

transformers safetensors gguf qwen2 text-generation conversational

Qwen-35B-A3B-SignOfFour-Coder-GGUF★ 8

transformers gguf merge ties dare moe

genpark-q-learning-temporal-difference-rl-skill★ 8

Autonomous Agent Tabular Q-Learning Temporal Difference Reinforcement Learning Engine with Epsilon-Greedy Exploration

genpark-byte-pair-encoding-bpe-tokenizer-skill★ 8

Autonomous Agent Byte-Pair Encoding (BPE) Subword Tokenizer Training & Compression Engine

genpark-multi-armed-bandit-ucb1-thompson-sampling-skill★ 8

Autonomous Agent Multi-Armed Bandit UCB1 & Thompson Sampling Exploration-Exploitation Optimizer

genpark-spike-timing-dependent-plasticity-stdp-skill★ 8

Spike-Timing-Dependent Plasticity (STDP) unsupervised Hebbian synaptic learning rule with asymmetric exponential long-term potentiation and depression.

Sailor-0.5B-Chat★ 8

transformers safetensors qwen2 text-generation multilingual sea

Orion-9B-Agentic-CodeCore-Merge-GGUF★ 8

transformers gguf text-generation-inference llama-cpp omnimergekit merge

jais-family-2p7b-chat★ 8

safetensors jais Arabic English LLM Decoder

IQuest-Coder-V1-40B-Instruct-GGUF★ 8

gguf text-generation-inference code agent swe-bench text-generation

LFM3-1.7B-Claude-Code-Safetensors★ 8

transformers safetensors lfm3 text-generation claude stepbystep

llm-agents-tora-code-7b-v1.0★ 8

gradio region:us

ChatGPT-finetuning-webui-nextjs★ 7

A user-friendly platform designed for effortless fine-tuning and testing of models

MultiModelOptimizer★ 7

MultiModelOptimizer: A Hierarchical Parameter Synchronization Approach for Joint Training of Multiple Transformer Models

DialogSmith★ 7

Fine-tune an LLM on your Telegram chats to replicate your writing style using LLaMA-Factory and LoRA

Chatbot-Deploy★ 7

My current project about building chatbot with deep neural networks. This repo show my chatbot code for deployment purpose

Parallel-Seq2Seq★ 7

A new seq2seq model for fast training.

scalapy-gym★ 7

A ScalaPy Facade for OpenAI Gym!

SARAN★ 7

SARAN: Shallow Auto-Regressive Attention Network

omnitoken★ 7

Pure-Go LLM tokenizer and tiktoken-compatible token counter for OpenAI BPE, WordPiece, SentencePiece, Gemini, Llama, Mistral, and Hugging Face adapters.

AgentTulu★ 7

gradio opengpt tulu llama community region:us

Native_1-bit_LLM★ 7

gradio region:us

DeepV★ 7

gradio region:us

Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q5_K_M-GGUF★ 7

docker region:us

SuperQwen-AgentWorld-35B-A3B-abliterated-mlx-4bit★ 7

mlx safetensors qwen3_5_moe qwen-agentworld abliterated 4-bit

albertlight-7b★ 7

transformers safetensors llama text-generation fr license:apache-2.0

gemma-2-27b-it-function-calling-GGUF★ 7

transformers safetensors gguf gemma2 text-generation conversational

Phi-3-mini-4k-instruct-function-calling★ 7

transformers safetensors phi3 text-generation conversational custom_code

jais-adapted-13b-chat★ 7

safetensors llama Arabic English LLM Decoder

llama-3-neural-chat-v1-8b-GGUF★ 7

transformers gguf text-generation dataset:mlabonne/orpo-dpo-mix-40k dataset:Open-Orca/SlimOrca-Dedup dataset:jondurbin/airoboros-3.2

leo-hessianai-13B-chat-bilingual-GGUF★ 7

transformers gguf llama text-generation en de

Vigogne-2-7B-Chat-GGUF★ 7

transformers gguf llama LLM llama-2 text-generation

Emollama-chat-7b★ 7

transformers safetensors llama text-generation en arxiv:2401.08508

leo-hessianai-13B-chat-GGUF★ 7

transformers gguf llama text-generation en de

openthaigpt-1.0.0-13b-chat★ 7

transformers safetensors gguf llama text-generation openthaigpt

qwen-chat-GGUF-14B★ 7

gguf qwen chat 中文 text-generation zh

Yi-1.5-6B-Chat-GGUF★ 7

gguf text-generation base_model:01-ai/Yi-1.5-6B-Chat base_model:quantized:01-ai/Yi-1.5-6B-Chat license:apache-2.0 endpoints_compatible

DeepSeek-V2-Chat-0628-GGUF★ 7

gguf text-generation base_model:deepseek-ai/DeepSeek-V2-Chat-0628 base_model:quantized:deepseek-ai/DeepSeek-V2-Chat-0628 license:other endpoints_compatible

Sailor2-20B-Chat★ 7

transformers safetensors qwen2 text-generation multilingual sea

Agents-A1-AWQ-INT4★ 7

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

Qwen3.6-27B-Tachibana-Agent★ 7

transformers safetensors qwen3_5_text text-generation tachibana valiant

Qwen2.5-Coder-32B-Instruct-bnb-4bit★ 7

transformers safetensors qwen2 text-generation unsloth code

IndustrialCoder-Thinking★ 7

transformers safetensors iquestcoder text-generation code industrial-code

SicariusSicariiStuff_Assistant_Pepe_70B-GGUF★ 7

gguf text-generation en dataset:SicariusSicariiStuff/UBW_Tapestries base_model:SicariusSicariiStuff/Assistant_Pepe_70B base_model:quantized:SicariusSicariiStuff

Qwen1.5-MoE-A2.7B-Chat-4bit★ 7

mlx safetensors qwen2_moe pretrained moe text-generation

Qwen2.5-Coder-7B-Q4_K_M-GGUF★ 7

transformers gguf code qwen qwen-coder codeqwen

GPT2-Small★ 7

streamlit region:us

Nemotron-3-Nano-4B-Coding-Agent-GGUF★ 7

gguf nemotron mamba2 coding function-calling tool-use

BananaMind-2-Medium-Chat★ 7

transformers safetensors bananamind2_medium text-generation causal-lm chat

internlm2-chat-20b-4bits★ 7

transformers pytorch internlm feature-extraction text-generation conversational

Neutrino-0.6B-Chat★ 7

transformers trtc_v4 text-generation ternary quantization trtc

KAT-Coder-V2.5-Dev-Imatrix-GGUF★ 7

gguf code agent agentic-coding moe coding

PLLuM-12B-chat-2512★ 7

safetensors mistral text-generation conversational pl arxiv:2511.03823

Qwen3-Coder-30B-A3B-GGUF★ 7

gguf atomic-chat qwen3 qwen llama.cpp quantized

AI-Chatbot-Conversation-Dataset★ 7

The original data contains 500k conversations, but this is just a sample. You can download the 10k dataset with personal and sensitive information removed.

jais-adapted-13b-chat★ 7

safetensors llama Arabic English LLM Decoder

AgentEvol-7B★ 7

transformers safetensors llama text-generation arxiv:2406.04151 text-generation-inference

CodeV-R1-RL-Qwen-7B★ 7

transformers safetensors qwen2 text-generation verilog conversational

Qwen3-Coder-Next-NVFP4★ 7

Model Optimizer safetensors qwen3_next nvidia ModelOpt Qwen3CoderNext

Qwen2.5-Coder-14B-Instruct-Uncensored★ 7

transformers safetensors qwen2 text-generation conversational en

Pebble-25M-Chat★ 7

transformers safetensors pebble_25m text-generation pebble language-model

jais-family-590m-chat★ 7

safetensors jais Arabic English LLM Decoder

genpark-ldpc-belief-propagation-decoder-skill★ 7

Production-grade genpark-ldpc-belief-propagation-decoder-skill skill for AI agents

genpark-surface-code-syndrome-decoder-skill★ 7

Rotated planar surface code syndrome decoder detecting bit-flip (X) and phase-flip (Z) errors using parity-check stabilizer measurements.

genpark-beam-search-autoregressive-decoder-skill★ 7

Production-grade genpark-beam-search-autoregressive-decoder-skill skill for AI agents

genpark-adamw-decoupled-weight-decay-skill★ 7

AdamW optimizer engine decoupling L2 weight decay regularization from adaptive gradient first and second moments.

genpark-ppo-clipped-surrogate-engine-skill★ 7

Proximal Policy Optimization (PPO) clipped surrogate objective engine maintaining stable trust-region policy updates and bounding gradient divergence.

genpark-sgdr-cosine-annealing-restarts-skill★ 7

SGDR: Stochastic Gradient Descent with Warm Restarts and Cosine Annealing learning rate schedule engine.

KAT-Coder-V2.5-Dev-OptiQ-4bit-REAP-18B★ 7

mlx safetensors qwen3_5_moe quantized expert-pruning reap

genpark-lookahead-k-step-optimizer-skill★ 7

Lookahead optimizer wrapper stabilizing optimization trajectories by interpolating fast and slow weights every k steps.

Qwen1.5-7B-Chat_mistral★ 7

transformers pytorch mistral text-generation qwen qwen1.5

chatbench-distilgpt2★ 7

transformers safetensors gpt2 text-generation Microsoft ChatBench

Triumvirate-Qwopus-MiMo-Ornith-9B-Coder-GGUF★ 7

gguf llama.cpp imatrix qwen qwen3.5 code

Groq-Llama-3-Groq-8B-Tool-Use★ 7

gradio region:us

fewshot-textclassification★ 6

Playing with SetFit approach for few-shot transfer for text classification

icr-kv-caching-long-context-llms★ 6

Exploring Fine-Tuning for In-Context Retrieval and Efficient KV-Caching in Long-Context Language Models

sparse★ 6

Delta Compression for Fine-tuned Models and Datasets

slm-agent★ 6

Small Language Model (SLM) Agent Finetuning Practice

Hybrid_LLM-based_Recommendation_Model★ 6

gradio region:us

Qwen35B-Agent-R2★ 6

transformers safetensors gguf qwen3_5_moe_text text-generation qwen

llama-3-8B-function-calling-GGUF★ 6

gguf text-generation endpoints_compatible region:us conversational

dolphin-2_6-phi-2-sft-glaive-function-calling-v2-ep1★ 6

transformers safetensors phi-msft text-generation conversational custom_code

vi-gemma-2-2b-function-calling★ 6

transformers safetensors gemma2 text-generation text-generation-inference unsloth

Gemma-7B-Instruct-Function-Calling★ 6

transformers safetensors gemma text-generation conversational license:cc

Llama3-8B-Function-Calling★ 6

transformers safetensors llama text-generation conversational license:llama3

Llama-2-7b-chat-hf-function-calling-GGML★ 6

facebook meta pytorch llama llama-2 functions

CodeLlama-34b-Instruct-hf-function-calling-v2★ 6

transformers safetensors llama text-generation facebook meta

Yi-6B-200K-Llamafied-function-calling-v2★ 6

transformers safetensors llama text-generation yi function calling

More in Agent frameworks & infrastructure