使用glm-2b时候，跟随readme提供的例子，得到很糟糕的输出

[leekum2018]

代码如下:
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("THUDM/glm-2b", trust_remote_code=True)
model = AutoModelForSeq2SeqLM.from_pretrained("THUDM/glm-2b", trust_remote_code=True)
model = model.half().cuda()
model.eval()

inputs = tokenizer("Ng is an adjunct professor at [MASK] (formerly associate professor and Director of its Stanford AI Lab or SAIL ). Also a pioneer in online education, Ng co-founded Coursera and deeplearning.ai.", return_tensors="pt")
inputs = tokenizer.build_inputs_for_generation(inputs, max_gen_length=512).to('cuda')
outputs = model.generate(**inputs, max_length=512, eos_token_id=tokenizer.eop_token_id)
print(tokenizer.decode(outputs[0].tolist()))

得到输出:
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Some weights of the model checkpoint at THUDM/glm-2b were not used when initializing GLMForConditionalGeneration: ['dense.weight', 'out_proj.bias', 'out_proj.weight', 'dense.bias']

• This IS expected if you are initializing GLMForConditionalGeneration from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
• This IS NOT expected if you are initializing GLMForConditionalGeneration from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
  The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's attention_mask to obtain reliable results.
  Setting pad_token_id to eos_token_id:50258 for open-end generation.
  [CLS] Ng is an adjunct professor at [MASK] (formerly associate professor and Director of its Stanford AI Lab or SAIL ). Also a pioneer in online education, Ng co-founded Coursera and deeplearning.ai.<|endoftext|> <|startofpiece|> 111111111 each1 when1111111 when11 each1 each1 each1 each1 each1 each1 each1 each1 each1 each1 each1 each1 each1 each111111111111111111111111111111111111111111111111111111 when11111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111

[kolaen]

同样的问题，请问解决了吗

[Xiang]

同问