README.md

metadata

base_model: Qwen/Qwen3.5-0.8B-Base
library_name: peft
pipeline_tag: text-generation
tags:
  - architecture
  - voxel
  - lora
  - transformers

ArchiCell

ArchiCell generates discrete architectural tokens from natural-language descriptions and decodes them into 64 x 64 x 64 voxel buildings.

This repository contains the inference weights for two stages of the ArchiCell pipeline:

• tokenizer/best.pt: Stage 1 structure-aware VQ tokenizer checkpoint.
• lora/: Stage 2 PEFT LoRA adapter and its tokenizer files for Qwen/Qwen3.5-0.8B-Base.

The Qwen base model is not duplicated here. Download it separately from Qwen/Qwen3.5-0.8B-Base.

Download

git lfs install
git clone https://huggingface.co/QiHoaran/ArchiCell weights/ArchiCell
git clone https://huggingface.co/Qwen/Qwen3.5-0.8B-Base models/Qwen3.5-0.8B-Base

Use with the ArchiCell source repository

python stage_3_inference/infer.py \
  --model_dir models/Qwen3.5-0.8B-Base \
  --lora_ckpt weights/ArchiCell/lora \
  --stage3_checkpoint weights/ArchiCell/tokenizer/best.pt \
  --out_dir outputs/my_run \
  --save_mode voxel

Source code and complete instructions: QiHoaran/ArchiCell on GitHub.

Weight details

• Base model: Qwen/Qwen3.5-0.8B-Base
• LoRA rank: 16
• LoRA alpha: 32
• LoRA target modules: q_proj, k_proj, v_proj, o_proj
• VQ codebook size: 1024
• Tokenizer input: 7 channels
• Tokenizer latent grid: 8 x 8 x 8
• Tokenizer output voxel grid: 64 x 64 x 64

The LoRA training-state checkpoint is intentionally excluded because it is only required for resuming training, not inference.

Status and limitations

These are research weights for the ArchiCell V1 pipeline. The Stage 1 checkpoint and Stage 2 adapter are published for inference and reproducibility; broader generalization has not been established.