Agent frameworks & infrastructure
Models, fine-tuning & training
2,504 agents · most starred first
Models, fine-tuning & training, page 14 of 26
mlx safetensors minimax_m3_vl vmlx jang reap
transformers safetensors gguf qwen3_5 image-text-to-text heretic
gguf gemma4 coding code python reasoning
gguf code qwen qwen-coder codeqwen text-generation
gradio region:us
transformers safetensors gguf qwen3_5_moe_text text-generation qwen
transformers safetensors qwen3_5_moe image-text-to-text moe qlora
transformers safetensors qwen2 text-generation unsloth code
transformers safetensors gguf qwen3_next text-generation qwen3
transformers safetensors dhara_ar text-generation diffusion-llm block-diffusion
safetensors qwen3_5_moe nvfp4 vllm compressed-tensors moe
mlx safetensors qwen3_5_moe qwen world-model agent
gguf cybersecurity quantized ollama llama-cpp text-generation
litert-lm tflite chat text-generation base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0 base_model:finetune:TinyLlama/TinyLlama-1.1B-Chat-v1.0
transformers gguf code codeqwen chat qwen
MLX Porting Toolkit — an agent-guided, evidence-gated pipeline (scaffold → convert → parity → benchmark) plus a portable skill for porting PyTorch/Hugging Face models to Apple MLX.
Penalize the Path, Reward the Outcome — verifiable per-action penalties as a dense channel for deployable, sample-efficient agentic RL (GRPO). Paper: arXiv:2607.07435
gguf text-generation code coding-assistant qwen2.5-coder en
gguf code agentic moe qwen3.6 dappit
mlx safetensors gemma4 4-bit quantized apple-silicon
peft safetensors text-generation conversational en arxiv:2409.11500
transformers safetensors mistral text-generation arxiv:2310.11511 arxiv:2306.02707
transformers gguf text-generation zh arxiv:1910.09700 license:apache-2.0
Learn LLM fine-tuning with an end-to-end guide for beginners and developers using Unsloth, LoRA, PEFT, and Google Colab
沉浸式 AI 大模型训练体验。亲手搭建数据中心、采集数据、研发前沿技术、训练大模型,挑战基准测试最高分。
Train (from scratch) tiny GGUF language models on WebGPU
transformers safetensors nemotron_h text-generation nvidia pytorch
⚡ Advanced AI iteration framework featuring an 8-stage pipeline, automated fine-tuning, voice interaction, and security scanning.
transformers gguf code codeqwen chat qwen
safetensors qwen3 speculative-decoding dspark dflash draft-model
transformers safetensors qwen3_5 text-generation qwen3.5 function-calling
transformers safetensors hrm_text text-generation function-calling tool-use
safetensors qwen3_5_text tool-calling function-calling agent edge-ai
transformers safetensors qwen3 text-generation littlelearner k5
gguf quantized GGUF imatrix quantization imat
gguf qwen2.5 qwen2.5-coder code abliteration uncensored
transformers safetensors qwen2 text-generation llama-factory lora
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.
safetensors qwen3 speculative-decoding dspark dflash draft-model
transformers gguf mistral quantized 2-bit 3-bit
transformers gguf code codeqwen chat qwen
transformers gguf qwen3_next heretic uncensored decensored
transformers safetensors qwen3_moe text-generation cantonese hong-kong
transformers gguf llama code math text-generation
gguf text-generation base_model:internlm/internlm2_5-20b-chat base_model:quantized:internlm/internlm2_5-20b-chat license:other endpoints_compatible
gguf text-generation base_model:andrewzh/Absolute_Zero_Reasoner-Coder-14b base_model:quantized:andrewzh/Absolute_Zero_Reasoner-Coder-14b endpoints_compatible re
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)
safetensors qwen2 chat GGUF text-generation conversational
Run and Fine-tune GGUF models, with LoRA or full weights, from SFT to agentic GRPO
transformers safetensors llama text-generation minicpm minicpm5
transformers safetensors qwen3_5 image-text-to-text text-generation-inference pytorch
transformers pytorch llama text-generation text-generation-inference endpoints_compatible
transformers safetensors qwen3 text-generation agent tool-use
safetensors gguf qwen2 code heretic uncensored
从零构建类 Qwen 3 Dense架构 / Deepseek MoE架构大语言模型,全链路打通“预训练、SFT、CoT蒸馏、GRPO 对齐与评测闭环”的端到端大模型训练管线。
Solving openAI's game 'Lunar-Lander' with Deep Reinforcement Learning
Local fine-tuning, pre-training and RAG for LLMs
Time Series Lean Notation for python, it is designed to maximize the token efficiency of time-series data to LLMs
Multi-agent DDPG on ml-agents environment
BharatwASI is an Artificial Super Intelligence (ASI) enabled chatbot, pioneering India's journey towards self-reliance in AI. Developed by Decima Technologies. This repository contains the source code, model training scripts, API implementation, and deployment instructions for BharatwASI. Join us in shaping the future of India's AI supremacy!
🧠 DataForge — An intelligent LLM fine-tuning dataset generator that transforms raw prompts into structured ShareGPT-format training data through a multi-stage AI pipeline. Built with FastAPI + React/TypeScript, featuring real-time progress tracking via SSE, and FAISS-powered deduplication. Just prompt it, and watch your dataset build itself. ⚡
Local LLM fine-tuning and chat for Apple Silicon
Behavior-driven cognitive experimentation toolkit with BCE (Behavioral Consciousness Engine) regularization, telemetry, and plug-and-play integrators for language-model training and evaluation.
[ACL 2026 Main] MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization
Agentic harness for iteratively improving a local LLM's structured-output quality, scored against a frontier-model gold standard.
Open-source rollout, verification, and trajectory plane for agentic reinforcement learning.
Seq2Seq implemented by MXNET
Create Datasets , FineTune Models , Test Models - All in one place. Everything simplified
An auto-updating AI Model Catalog - Single binary CLI, REST/SSE Server - SDKs - Golang Package.
streamlit region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
transformers gguf qwen world-model agent environment-simulation
gguf gemma4 coding agentic terminal tool-use
transformers safetensors qwen3_5_moe image-text-to-text qwen unsloth
gguf text-generation en de ar license:apache-2.0
gguf facebook meta pytorch llama llama-3
gguf quantized 2-bit 3-bit 4-bit 5-bit
transformers safetensors llama text-generation text-generation-inference unsloth
transformers gguf mistral quantized 2-bit 3-bit
safetensors gemma4_assistant tensorizer modelopt nvidia fp4
transformers safetensors llama text-generation llm long context
transformers safetensors llama text-generation conversational zh
transformers safetensors sdar text-generation conversational custom_code
transformers safetensors mistral text-generation sft it
transformers gguf llama text-generation base_model:deepseek-ai/deepseek-llm-7b-chat base_model:quantized:deepseek-ai/deepseek-llm-7b-chat
transformers gguf llama text-generation en de
transformers safetensors llama text-generation unsloth llama-2
transformers gguf mistral quantized 2-bit 3-bit
transformers gguf llama text-generation base_model:01-ai/Yi-1.5-34B-Chat base_model:quantized:01-ai/Yi-1.5-34B-Chat
transformers gguf llama llama-2 text-generation en
transformers gguf llama text-generation en de
transformers pytorch gpt2 text-generation text-generation-inference endpoints_compatible
transformers safetensors qwen2 text-generation chat conversational
transformers gguf qwen2 text-generation chat en
transformers safetensors qwen3_moe text-generation qwen3 qwen