import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the HelpingAI2.5-2B model
model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI2.5-2B")
# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI2.5-2B")

# Define the chat input
chat = [
    { "role": "system", "content": "You are HelpingAI, an emotional AI. Always answer my questions in the HelpingAI style." },
    { "role": "user", "content": "GIVE ME YOUR INTRO" }
]

inputs = tokenizer.apply_chat_template(
    chat,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

# Generate text
outputs = model.generate(
    inputs,
    max_new_tokens=256,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)

response = outputs[0][inputs.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))