import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

REPO = "IvmeLabs/Ivme-Conversate-P-v1"
model = AutoModelForCausalLM.from_pretrained(REPO, trust_remote_code=True, dtype=torch.float32)
tokenizer = AutoTokenizer.from_pretrained(REPO, trust_remote_code=True)
model.eval()

prompt = "Once upon a time, there was a"
inputs = tokenizer(prompt, return_tensors="pt")
out = model.generate(
    **inputs, max_new_tokens=200, do_sample=True,
    temperature=0.8, top_k=40, pad_token_id=tokenizer.pad_token_id,
)
print(tokenizer.decode(out[0], skip_special_tokens=True))