keisuke-miyako/h2o-danube3.1-4b-chat-onnx-int4-NG

⚠️ Do not use with onnxruntime-genai; model architecture has a non-standard head size of 120 which is not divisible by 16.

from google.colab import drive
drive.mount('/content/drive')

!pip install "optimum[onnxruntime-gpu]" transformers
!pip install numpy onnxruntime-genai

from huggingface_hub import snapshot_download
import os

# --- STEP 1: Download the model locally ---
print("Downloading model snapshot to local disk...")
# We use Python here so we don't need the flag in the command line later
local_model_path = snapshot_download(
    repo_id="h2oai/h2o-danube3.1-4b-chat", 
    ignore_patterns=["*.msgpack", "*.h5", "*.ot"] # Skip useless files to save speed
)
print(f"Model downloaded to: {local_model_path}")

# --- STEP 2: Run the Builder on the local files ---
# We pass the local path variable to the command using '$'
print("Starting INT4 Conversion...")

!python -m onnxruntime_genai.models.builder \
    -m "$local_model_path" \
    -o "/content/drive/My Drive/Danube_3_1_INT4_CPU" \
    -p int4 \
    -e cpu

print("REAL SUCCESS! Check your Drive folder: Danube_INT4_CPU")