Regex-Helper (Powered by ML-Forge)
Precision Regular Expression Assistant built using a specialized fine-tuning pipeline.
🏗 ML-Forge Workflow
This model is generated using the ML-Forge engine, a parameterized automation stack for rapid LLM development.
🚀 Rapid Start
Follow these steps to go from zero to a published model:
1. Initialize
Sets up the base Llama 3.2 weight.
./scripts/setup.sh
2. Prepare Data
Pulls bndis/regex_instructions from Hugging Face and cleans it.
source config.sh
uv run python scripts/data_prep.py
3. Train
Starts the LoRA training session (1000 iterations, Rank 16).
./scripts/train.sh
4. Publish
Fuses weights, creates GGUFs, and pushes to HF, Ollama, and Kaggle.
./scripts/publish.sh
📊 Technical Configuration
Parameters are managed in config.sh:
- Base: Llama 3.2 3B Instruct
- Rank: 16
- Context: 2048 tokens
- Precision: Q4_K_M (Ollama) / BF16 (HF)
Created by the ML-Forge Pipeline.