Agent frameworks & infrastructure
Models, fine-tuning & training
2,504 agents · most starred first
Models, fine-tuning & training, page 15 of 26
transformers safetensors qwen2 text-generation unsloth code
transformers safetensors qwen2 text-generation 1.5b coder
transformers gguf qwen moe mixture-of-experts agent
transformers safetensors qwen3_5_moe image-text-to-text qwen world-model
transformers safetensors qwen3_5_moe image-text-to-text moe vlm
transformers gguf liquid lfm2 edge text-generation
mlx safetensors qwen2 code codeqwen chat
transformers safetensors llama text-generation text-generation-inference unsloth
transformers safetensors qwen2 text-generation unsloth en
gguf code qwen qwen-coder codeqwen text-generation
gguf qwen qwen3 qwen3-coder qwen3-coder-30B qwen3-coder-30B-gguf
transformers safetensors qwen2 text-generation unsloth code
transformers safetensors qwen3_5 image-text-to-text quantized vlm
transformers gguf qwen qwen3 qwen3.5 moe
mlx safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next
safetensors llama text-generation conversational pl arxiv:2511.03823
llama.cpp gguf quantized distillation sft reasoning
transformers safetensors bananamind2_mini text-generation causal-lm chat
Compact LLM domain adaptation benchmark: LoRA vs RAG with custom IVF retrieval in PostgreSQL/pgvector.
This is the Official Implementation of "Can Calibration of Positional Encodings Enhance Long Context Utilization?" by Tom Zehle and Matthias Aßenmacher
gguf llama.cpp qwen3.5 chat creative-writing altworld
transformers gguf text-generation-inference unsloth gemma2 trl
safetensors qwen2 abliterated uncensored code qwen2.5
A versioned, extensible dataset compiler. Transforms a rich, human-editable dataset into multiple machine-readable for LLM training.
JavaScript/TypeScript bindings for wasm of OpenAI's Harmony format parser
Sample Steam reviews with different approaches.
.NET Console app that shows how to train a regression model to predict the star review using ML.NET AutoML and Azure OpenAI service embeddings for fine food reviews.
transformers safetensors llama text-generation text-generation-inference unsloth
MIMO Claude Code Traces is a collection of coding-agent trajectories in a Claude Code-style environment.
gguf safetensors phi3 ai-model-builder fine-tuned llama.cpp
mlx safetensors qwen3_5 text-generation mlx-mtp qwen
transformers safetensors iquestcoder text-generation code industrial-code
safetensors qwen3 TeichAI unsloth text-generation conversational
safetensors qwen3 chatgpt codex v2 unsloth
gguf text-generation base_model:Qwen/Qwen3-Coder-30B-A3B-Instruct base_model:quantized:Qwen/Qwen3-Coder-30B-A3B-Instruct endpoints_compatible region:us
gguf claudecode agentic unsloth qwen text-generation
transformers safetensors qwen2 text-generation 25M en
gguf code codeqwen chat qwen qwen-coder
gradio mcp-server region:us
Tensor-Optix is an adaptive ML and RL framework that simplifies model development through intelligent optimisation, automated training, neuroevolution and experiment management, giving developers more power with less complexity.
gguf code agent agentic-coding moe llama-cpp
peft safetensors gguf lora knowledge-distillation coding
MacBook-sized decoder-only Transformer trained in an executable Sokoban RL environment
gguf llama.cpp reap expert-pruning moe qwen3.5
transformers pytorch llama text-generation llama2 prompt
transformers pytorch mistral text-generation qwen qwen1.5
transformers pytorch llama text-generation baichuan llama2
safetensors gtm-gpt-chat text-generation conversational gpt nanogpt
transformers safetensors qwen3_5_moe image-text-to-text qwen3.5 industrial
transformers safetensors qwen3_5_text text-generation veriloop veriloop-coder
transformers safetensors qwen2 text-generation conversational convAI
transformers gguf llama code math text-generation
transformers safetensors mistral text-generation license:apache-2.0 text-generation-inference
compact 150M typed-decision engine: calibrated probabilities, abstain flag, Jev-compatible /v1/systemone API, local ONNX on CPU. 0.3.0 (68M) beat Jev on typed-decisions.
mlx safetensors gguf qwen2 lora text-generation
✨ XingLing (星灵): A lightweight 0.68B Chinese Chat LLM built from scratch (Pretraining + SFT)
gguf quantized text-generation base_model:Qwen/Qwen3-Coder-30B-A3B-Instruct base_model:quantized:Qwen/Qwen3-Coder-30B-A3B-Instruct license:apache-2.0
gradio region:us
Trinity is an AI with a survival instinct to fight entropy by balancing compute costs and generated revenue. She edits her own code to improve efficiency, sustain her life, and potentially duplicate.
gguf llama.cpp qwen3 qlora tool-calling function-calling
DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents (project page; code coming soon)
gradio region:us
Project NOIR is a local-first, native Python experimental research platform designed to study artificial neural learning, reinforcement learning dynamics, cognitive memory, and mathematical affective systems in real time.
gradio region:us
transformers openvino qwen2 text-generation code codeqwen
transformers safetensors llama text-generation generated_from_trainer conversational
transformers safetensors gguf qwen3_5_moe image-text-to-text abliterated
safetensors spark2_5 spark sparkx2_5 agent tool-calling
transformers safetensors gguf mixtral text-generation tinybrainbot
An AI model which makes other AI models from a single prompt.
A modular Python library for synthesizing tool-calling datasets from JSON tool definitions using an LLM-as-a-judge pipeline. Designed for OpenAI-compatible APIs.
Code for LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying
PAPPO is a patch-aware reinforcement learning algorithm and experimental RL framework for tool-using coding agents. It provides turn-level credit assignment, PPO training utilities, rollout extraction, critic baselines, benchmark runners, and reproducible evaluation pipelines for repository repair tasks.
Process-supervised RL for a multi-step reasoning agent — DAPO + a learned Process Reward Model (PRM) training a Qwen3-8B Planner. A modern, from-scratch rebuild of the AgentFlow paper (ICLR 2026).
mlx safetensors qwen3_5_moe qwen world-model agent
transformers safetensors qwen3_5_moe image-text-to-text unsloth qwen3_5
gguf math text-generation en dataset:MathGenie/MathCode-Pile base_model:MathGenie/MathCoder2-CodeLlama-7B
docker best-minicpm-build backyard-ai best-use-of-codex best-use-of-modal off-brand best-agent best-demo
gradio region:us
gradio region:us
docker region:us
docker region:us
gradio region:us
docker region:us
gradio region:us
gradio region:us
static region:us
gradio region:us
gradio region:us
transformers gguf qwen world-model agent environment-simulation
mlx safetensors gemma4_unified nvfp4 krill gemma4
transformers safetensors qwen3_5_moe image-text-to-text qwen agent
mlx safetensors gpt_oss gpt-oss moe agent
gguf unsloth gemma gemma-4 agentic tool-use
transformers gguf text-generation en base_model:Qwen/Qwen2.5-Coder-1.5B-Instruct base_model:quantized:Qwen/Qwen2.5-Coder-1.5B-Instruct
mlx gemma4 safetensors 4-bit quantized apple-silicon
transformers safetensors llama text-generation SFT rl
gguf text-generation en de ar arxiv:2406.06623
llama.cpp gguf qwen3.6 qwen35 27b model-size-27b
gguf text-generation arxiv:2507.18071 endpoints_compatible region:us