CoolFace
Modelpublic

NikitaKlimenko/HypergraphFormer

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face
0likes
Model Card

HypergraphFormer

Link to paper: https://arxiv.org/abs/2605.18932 LoRA adapters fine-tuning Qwen/Qwen3-4B-Instruct-2507 for hypergraph-based floorplan generation. The repo contains several adapters trained on different dataset sizes.

Checkpoints

SubfolderTrain samplesStep
qwen_hypergraphformer_1000_samples/checkpoint-2401,000240
qwen_hypergraphformer_5000_samples/checkpoint-7505,000750
qwen_hypergraphformer_10000_samples/checkpoint-150010,0001500
qwen_hypergraphformer_25000_samples/checkpoint-390025,0003900
qwen_hypergraphformer/checkpoint-8700full8700

LoRA configuration

  • —Rank r = 64, lora_alpha = 128, lora_dropout = 0.1
  • —Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
  • —Task: CAUSAL_LM

Usage

python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_id = "Qwen/Qwen3-4B-Instruct-2507"
repo_id = "NikitaKlimenko/HypergraphFormer"
subfolder = "qwen_hypergraphformer_25000_samples/checkpoint-3900"

tok = AutoTokenizer.from_pretrained(repo_id, subfolder=subfolder)
base = AutoModelForCausalLM.from_pretrained(base_id, torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(base, repo_id, subfolder=subfolder)