File size: 1,726 Bytes
a517021 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 | """Download the Hugging Face checkpoint and run one typed Choice prediction."""
from __future__ import annotations
import sys
from pathlib import Path
import torch
from huggingface_hub import snapshot_download
REPO_ID = "Syigen/rgcm"
def main() -> None:
repo_path = Path(snapshot_download(REPO_ID))
# The model repo ships this small runtime package beside the checkpoint.
sys.path.insert(0, str(repo_path))
from concept_memory import ConceptMemoryModel
from concept_memory.types import Question
checkpoint = repo_path / "model.pt"
payload = torch.load(checkpoint, map_location="cpu", weights_only=False)
model = ConceptMemoryModel.from_pretrained(
payload["encoder"],
decision_size=payload["decision_size"],
max_length=payload["max_length"],
)
model.load_state_dict(payload["model_state_dict"])
model.eval()
question = Question(
id="intent",
type="choice",
instructions="Which team should handle this customer request?",
criteria=[
{"id": "billing", "description": "Payment or subscription issues"},
{"id": "technical", "description": "Bugs or integration problems"},
{"id": "sales", "description": "Pricing or account questions"},
],
)
with torch.inference_mode():
result = model.predict(
"Stripe integration keeps failing after several attempts.", [question]
)[0]
criteria = question.normalized_criteria()
predicted = criteria[result.prediction.item()]
print(f"Prediction: {predicted.id} - {predicted.description}")
print("Probabilities:", result.probabilities.tolist())
if __name__ == "__main__":
main()
|