from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "lmstudio-community/DeepSeek-R1-Distill-Qwen-1.5B-GGUF"
filename = "DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf"

tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename)

model.save_pretrained('./converted_model')
tokenizer.save_pretrained('./converted_model')

# text = "What is 1+2+3+4+5+6+7+8+9+10?"    

# inputs = tokenizer(text, return_tensors="pt")
# outputs = model.generate(**inputs, max_new_tokens=512)
# print(tokenizer.decode(outputs[0], skip_special_tokens=False))