0

Huggingface上的预训练facebook/bart-base模型可用模型，将“beam_search”参数设置为 4。[检查附加的字段配置文件]

这是否意味着模型隐式使用“beam_search=4”，并且我们在使用 model.generate 函数时不需要提供额外的 beam_search 参数？

text = "this is a dummy string"

model = AutoModelForSeq2SeqLM.from_pretrained('facebook/bart-base')
tokenizer = AutoTokenizer.from_pretrained('facebook/bart-base')


inputs = tokenizer(text, max_length=128, return_tensors='pt')

output_sequences = model.generate(input_ids=inputs['input_ids'],\
                                   max_length=128,\
                                   num_beams=3,\
                                   do_sample=True,\
                                   top_k=0,\
                                   top_p=0.95,\
                                   early_stopping=True, \
                                   no_repeat_ngram_size=5)
generated_text = tokenizer.batch_decode(output_sequences , skip_special_tokens=True)[0]

以下是模型的 config.json 文件

{
  "_name_or_path": "bart-base",
  "activation_dropout": 0.1,
  "activation_function": "gelu",
  "add_bias_logits": false,
  "add_final_layer_norm": false,
  "architectures": [
    "BartModel"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 0,
  "classif_dropout": 0.1,
  "classifier_dropout": 0.0,
  "d_model": 768,
  "decoder_attention_heads": 12,
  "decoder_ffn_dim": 3072,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 6,
  "decoder_start_token_id": 2,
  "dropout": 0.1,
  "early_stopping": true,
  "encoder_attention_heads": 12,
  "encoder_ffn_dim": 3072,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 6,
  "eos_token_id": 2,
  "forced_eos_token_id": 2,
  "gradient_checkpointing": false,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2"
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2
  },
  "max_position_embeddings": 1024,
  "model_type": "bart",
  "no_repeat_ngram_size": 3,
  "normalize_before": false,
  "normalize_embedding": true,
  "num_beams": 4,
  "num_hidden_layers": 6,
  "pad_token_id": 1,
  "scale_embedding": false,
  "task_specific_params": {
    "summarization": {
      "length_penalty": 1.0,
      "max_length": 128,
      "min_length": 12,
      "num_beams": 4
    },
    "summarization_cnn": {
      "length_penalty": 2.0,
      "max_length": 142,
      "min_length": 56,
      "num_beams": 4
    },
    "summarization_xsum": {
      "length_penalty": 1.0,
      "max_length": 62,
      "min_length": 11,
      "num_beams": 6
    }
  },
  "torch_dtype": "float32",
  "transformers_version": "4.12.0.dev0",
  "use_cache": true,
  "vocab_size": 50265
}
4

0 回答 0