luminousresearch/L0-Luau-1B-Instruct

GGUF

GGUF quantizations are available here: https://huggingface.co/mradermacher/Llama_L0-Luau-1B-GGUF

Training Data

This model was trained on a dataset derived from TorpedoSoftware/Roblox-Luau-Reasoning-v1.0, which is released under the MIT License.

The original authors are not affiliated with or responsible for this model.

Base Model

Base model: meta-llama/Llama-3.2-1B-Instruct

Fine-tuning Method

• —Adapter: DoRA
• —Method: SFT
• —Precision: trained with 4-bit base weights + BF16 compute, then merged to safetensors

Training Details

• —Training time: ~12 hours
• —Hardware: 1x NVIDIA RTX 5060 Ti