Doriandarko / MLX-GRPO
A pure MLX-based training pipeline for fine-tuning LLMs using GRPO on Apple Silicon.
☆37Updated 3 months ago
Alternatives and similar repositories for MLX-GRPO:
Users that are interested in MLX-GRPO are comparing it to the libraries listed below
- Leveraging DSPy for AI-driven task understanding and solution generation, the Self-Discover Framework automates problem-solving through r…☆60Updated 9 months ago
- ☆41Updated last year
- auto fine tune of models with synthetic data☆75Updated last year
- A couple scripts to grab stats from email☆42Updated 8 months ago
- Very minimal (and stateless) agent framework☆43Updated 3 months ago
- ☆29Updated 5 months ago
- tiny_fnc_engine is a minimal python library that provides a flexible engine for calling functions extracted from a LLM.☆38Updated 8 months ago
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆90Updated 3 months ago
- Example implementation of Iteration of Tought - Gives a star if you like the project☆41Updated 4 months ago
- A Python library to orchestrate LLMs in a neural network-inspired structure☆47Updated 7 months ago
- RAG example using DSPy, Gradio, FastAPI☆79Updated last year
- ☆17Updated last year
- Starter app for creating an AI task completion agent with gmail capabilities.☆27Updated 10 months ago
- A Python package to dynamically load functions for OpenAI Assistant☆54Updated last year
- The original BabyAGI, updated with LiteLLM and no vector database reliance (csv instead)☆21Updated 7 months ago
- Minimal, clean code implementation of RAG with mlx using gguf model weights☆49Updated last year
- ☆47Updated last year
- ☆85Updated 3 months ago
- MCP Server to run python code locally☆53Updated 5 months ago
- OpenAI GPT hosted Agent Framework for Windows and MacOS☆36Updated 10 months ago
- Very basic framework for composable parameterized large language model (Q)LoRA / (Q)Dora fine-tuning using mlx, mlx_lm, and OgbujiPT.☆40Updated 2 months ago
- Thoughtful Lightning AI Assistant - Dual-engine system with DeepSeek reasoning and Groq inference, featuring Gradio UI, secure API manage…☆20Updated 3 months ago
- The next evolution of Agents☆48Updated 3 weeks ago
- An intelligent code optimization system leveraging AI analysis, automated refactoring, and test generation. Built with DSPy and Gradio, i…☆18Updated 3 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆52Updated 3 months ago
- A command-line utility to manage MLX models between your Hugging Face cache and LM Studio.☆39Updated 2 months ago
- uses all reasoning models in parallel and synthesizes an answer with o1. also has multi-chat where you can chat with any of them☆38Updated 3 months ago
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆74Updated last week
- A seamless matchmaking application that is programmed with Cohere Command R+, Stanford NLP DSPy framework, Weaviate Vector store and Crew…☆59Updated last year
- Turns an Airtable base into a WebGL knowledge graph leveraging relational columns☆33Updated last year