import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
compute_dtype = torch.bfloat16
device   = 'cuda'
model_id = "mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0"

model     = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=compute_dtype, attn_implementation="sdpa", device_map=device)
tokenizer = AutoTokenizer.from_pretrained(model_id)

chat    = tokenizer.apply_chat_template([{"role":"user", "content":"What is 1.5+102.2?"}], tokenize=True, add_generation_prompt=True, return_tensors="pt")
outputs = model.generate(chat.to(device), max_new_tokens=1024, do_sample=True) 
print(tokenizer.decode(outputs[0]))