code-act
Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.
- 1.7k
- Python
- MIT
- 3 y ago
Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.
Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.
LLM (Large Language Model) FineTuning
Build your own offline AI from any documents. Free. No coding. LoRA fine-tuning + RAG + GGUF export.
Distributed Reinforcement Learning for LLM Fine-Tuning with multi-GPU utilization
high-efficiency text & file scraper with smart tracking, client/server networking for building language model datasets fast
Train Studio - SFT LoRA Web UI (Gradio): hardware detect, GPU select, config, train/resume, merge tool
A helper library for fine-tuning Amazon Bedrock models. This toolkit assists in generating Q&A datasets from documents and streamlines the LLM fine-tuning process.
🧠 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. ⚡
A comprehensive, hands-on tutorial series for fine-tuning small language models using modern techniques. From foundations to advanced alignment methods.
20 runnable multi-GPU notebooks for Kaggle 2xT4: SFT, LoRA/QLoRA, DPO/GRPO alignment, and agent-trace eval
A payload compression toolkit that makes it easy to create ideal data structures for LLMs; from training data to chain payloads.
This project is an AI-powered algebra tutor using the Phi-3 Mini model. It provides personalized learning through interactive chat, adapting to the student's level and offering detailed step-by-step solutions. Built with Streamlit for an engaging educational experience.
Analytics Copilot (Text-to-SQL) is an end-to-end LLM engineering project that builds a production-style Natural Language → SQL assistant. It fine-tunes Mistral-7B-Instruct using QLoRA/LoRA adapters on the b-mc2/sql-create-context dataset, trains with a clean instruction-tuning prompt format, and ships a complete evaluation + deployment workflow.
LLM fine Tuning Dashboard is built using Next.Js, Tailwind CSS. It has just the front end components with hardcoded data and no backend integration yet.
LLM Fine-tuning and evaluating large language models
FlowerTune LLM on Finance Dataset (sentiment analysis)
Reproducible NL2SQL fine-tuning and multi-path inference benchmark on Spider/BIRD using Qwen2.5-Coder-7B and one NVIDIA L20 GPU.
A streamlined implementation for fine-tuning Meta's LLaMA 3.1 8B Instruct model using LoRA (Low-Rank Adaptation) with the PEFT library. This script enables efficient parameter-efficient fine-tuning on custom conversational datasets.