KnowRL-DeepSeek-R1-Distill-Qwen-7B

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Set the device
device = "cuda" if torch.cuda.is_available() else "cpu"

# Load the model and tokenizer
model_name = "zjunlp/KnowRL-DeepSeek-R1-Distill-Qwen-7B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16).to(device)

# Define the prompt using the model's template
prompt = "What is the main function of the mitochondria?"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

# Generate a response
inputs = tokenizer(text, return_tensors="pt").to(device)
outputs = model.generate(**inputs, max_new_tokens=512)

# Decode and print the output
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)