Affine-whiz-5Di55BGTjiQfcWVKKinaV7gdHXVLRa2akWKohuhw6ifHFSTQ

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "weirek/Affine-whiz-5Di55BGTjiQfcWVKKinaV7gdHXVLRa2akWKohuhw6ifHFSTQ",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("weirek/Affine-whiz-5Di55BGTjiQfcWVKKinaV7gdHXVLRa2akWKohuhw6ifHFSTQ")

# Generate text
messages = [
    {"role": "user", "content": "Hello, how are you?"}
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))