up_model

추론 시 lm-eval-harness 의 ARC 기본 prompt 형식 사용 (Question: {q}\nAnswer: {a})

[추론 예시]

from transformers import AutoModelForCausalLM, AutoTokenizer                                                                                                          
                                                                                                                                                                        
model_id = "torchtorchkimtorch/up_model"                                                                                           
 
tokenizer = AutoTokenizer.from_pretrained(model_id)                                                                                                                   
model = AutoModelForCausalLM.from_pretrained(model_id)    
                                                                                                                                                                      
prompt = "Question: What do cells break down to produce energy?\nAnswer:"                                                                                             
inputs = tokenizer(prompt, return_tensors="pt")                                                                                                                       
outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)                                                                                               
print(tokenizer.decode(outputs[0], skip_special_tokens=True))