---
license: cc-by-nc-nd-4.0
language:
- en
tags:
- luna
- sft
- lora
- rag
- mcp
- training
---

# LUNA-Training — SFT & LoRA Recipes for LUNA-100M

This repository is the **supervised fine-tuning workspace** for the [LUNA-100M](https://huggingface.co/ASTERIZER/LUNA-100M) model. It contains the SFT/LoRA training code, configuration files, and the RAG + MCP dataset build pipeline used to produce the trained `sft_v1` / `luna_100m_sft` checkpoints.

## Contents

| Path | Description |
|---|---|
| `train.py` | Base pretraining trainer (shared with the [LUNA workspace](https://huggingface.co/spaces/ASTERIZER/LUNA)) |
| `sft_train.py` | Full supervised fine-tuning trainer |
| `lora_sft_train.py` | LoRA SFT trainer (RAG+MCP adapter runs) |
| `lora_chat.py` / `chat.py` / `chat_full_sft.py` / `generate.py` | Inference / chat entry points |
| `validate_sft.py` / `validate_and_quantize.py` | Eval + quantization (incl. GGUF export) |
| `rag_mcp_lora_config.yaml` / `rag_mcp_full_sft_config.yaml` | RAG + MCP SFT recipes |
| `sft_config.yaml` / `train_config.yaml` | Base SFT / pretrain configs |
| `push_*_to_hf.py` | Upload helpers (code / dataset / model / LoRA) |
| `Base/Datasets/rag_mcp_sft/` | RAG + MCP SFT dataset builder + reports |
| `Base/checkpoints/EleutherAI/pythia-160m/` | LUNA tokenizer (vocab 50,254) |

## Related

- **Model:** [ASTERIZER/LUNA-100M](https://huggingface.co/ASTERIZER/LUNA-100M)
- **SFT dataset:** [ASTERIZER/LUNA-RAG-MCP-SFT-10M](https://huggingface.co/datasets/ASTERIZER/LUNA-RAG-MCP-SFT-10M)
- **Pretrain corpus:** [ASTERIZER/LUNA_PreTrain](https://huggingface.co/datasets/ASTERIZER/LUNA_PreTrain)
- **Program collection:** [LUNA-100M Program](https://huggingface.co/collections/ASTERIZER/luna-100m-program-6a9115383c18e52460bf67c9)