Preview LoRA adapter for hospitality receptionist experiments.
This is an adapter-only release. It is not a standalone model. Load it with the base model:
This is a preview research adapter, not a production hotel receptionist system.
It may produce incorrect, incomplete, or overconfident answers.
Do not use it to make booking, payment, legal, safety, privacy, or operational decisions without a verified PMS/tool layer and human review.
Use the processor/tokenizer from the base model unless you intentionally need a local copy:
1from peft import PeftModel
2from transformers import AutoProcessor, AutoModelForCausalLM
3
4base_model_id = "google/gemma-4-E2B-it"
5adapter_id = "chuanman2707/capyinn-gemma4-e2b-it-lora-v1-preview"
6
7processor = AutoProcessor.from_pretrained(base_model_id)
8model = AutoModelForCausalLM.from_pretrained(base_model_id)
9model = PeftModel.from_pretrained(model, adapter_id)
If the base model requires a different Transformers auto class in your environment, use the same class that successfully loads google/gemma-4-E2B-it.
