from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("ping98k/open-llama-3b-opus-reasoning-sft-2k-4bit", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("ping98k/open-llama-3b-opus-reasoning-sft-2k-4bit")

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is 10 * 5?"},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)
print(tokenizer.decode(output[0], skip_special_tokens=False))

LoRA adapter

See ping98k/open-llama-3b-opus-reasoning-sft-lora-2k