bigai-nlco / loogle Goto Github PK

Contributors

Stargazers

Forkers

eltociear qshuang123 liuying121288 yofuria jeda-hh

if len(tokenized_prompt) > max_length:
    half = int(max_length/2)
    prompt = tokenizer.decode(tokenized_prompt[:half], skip_special_tokens=True) + tokenizer.decode(tokenized_prompt[-half:], skip_special_tokens=True)

ans, groundtruth = [], []
preds = {}
raw_inputs = data_instance['input']
if data_instance['qa_pairs'] == 'none':
    preds['qa_pairs'] = data_instance['qa_pairs']
    json_obj = {'input': raw_inputs}

    prompt = prompt_format.format(**json_obj)
    tokenized_prompt = tokenizer(prompt, truncation=False, return_tensors="pt").input_ids[0]
    if len(tokenized_prompt) > max_length:
        half = int(max_length/2)
        prompt = tokenizer.decode(tokenized_prompt[:half], skip_special_tokens=True)+tokenizer.decode(tokenized_prompt[-half:], skip_special_tokens=True)
    
    
    input_ids = tokenizer(prompt, truncation=True, return_tensors="pt").input_ids.to(device)
    context_length = input_ids.shape[-1]
    with torch.no_grad():
        output = model.generate(input_ids,max_new_tokens=max_gen,temperature=1.0,num_beams=1,do_sample=False,repetition_penalty=float(2))[0]
    pred = tokenizer.decode(output[context_length:], skip_special_tokens=True)

    ans.append(pred)
    groundtruth.append(raw_inputs)