Generative Floor Plan Design with LLMs via RLVR
Collection
LoRA-based SFT adapters and RLVR-trained checkpoints for RPLAN floor-plan generation with Llama-3.3-70B-Instruct. • 9 items • Updated • 1
fp8-sft-Llama3.3-70B
LoRA SFT adapter for generating 8-room RPLAN floor plans from structured room and adjacency specifications.
Model Details
- Base model:
meta-llama/Llama-3.3-70B-Instruct - Local training base path:
models/Llama-3.3-70B-Instruct - Adapter type: LoRA / PEFT
- LoRA rank: 64
- LoRA alpha: 128
- Training stage: supervised fine-tuning (SFT)
- Task: RPLAN 8-room floor-plan generation
- Local source:
output/final/rplan8_2_70B_r64_a128_all
Reported SFT Metrics
| Metric | Value |
|---|---|
| Room Area error | 0.08 +/- 0.05 |
| Room ID recall | 1.00 +/- 0.00 |
| Overlap | 0.37 +/- 0.48 |
| Percent overlap | 0.01 +/- 0.03 |
| Compatibility | 0.41 +/- 0.73 |
| Diversity | 6.44 +/- 0.00 |
Intended Use
Use this adapter with the Llama-3.3-70B-Instruct base model to generate 8-room residential floor plans in the JSON format used by the paper. It is intended for research and evaluation on RPLAN-style floor-plan generation.
Limitations
The model is specialized to the 8-room RPLAN task and may not generalize to other datasets, room-count regimes, architectural standards, or safety-critical design workflows.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ludolara/fp8-sft-Llama3.3-70B
Base model
meta-llama/Llama-3.1-70B Finetuned
meta-llama/Llama-3.3-70B-Instruct