ReaRev GNN Model

Trained ReaRev GNN model for Knowledge Graph Question Answering.

Training Results

  • Best MRR: 0.4291
  • Best Epoch: 10
  • Architecture:
    • Hidden dim: 100
    • Layers: 3
    • Stages: 2

Usage

import torch
from huggingface_hub import hf_hub_download

# Download model
model_path = hf_hub_download(
    repo_id="zaineb2000/rearev-gnn-synthetic",
    filename="model.pt"
)

# Load model (requires ReaRevReasoner class)
checkpoint = torch.load(model_path)
model.load_state_dict(checkpoint['model_state_dict'])
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support