This notebook regroups the code sample of the video below, which is a part of the Hugging Face course.

In [ ]:

#@title
from IPython.display import HTML

HTML('<iframe width="560" height="315" src="https://www.youtube.com/embed/AhChOFRegn4?rel=0&amp;controls=0&amp;showinfo=0" frameborder="0" allowfullscreen></iframe>')

Out[ ]:

Install the Transformers and Datasets libraries to run this notebook.

In [ ]:

! pip install datasets transformers[sentencepiece]

In [ ]:

from transformers import AutoModel

bert_model = AutoModel.from_pretrained("bert-base-cased")
print(type(bert_model))

gpt_model = AutoModel.from_pretrained("gpt2")
print(type(gpt_model))

bart_model = AutoModel.from_pretrained("facebook/bart-base")
print(type(bart_model))

Some weights of the model checkpoint at bert-base-cased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.seq_relationship.weight', 'cls.predictions.decoder.weight', 'cls.predictions.transform.dense.weight', 'cls.predictions.bias', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.bias']
- This IS expected if you are initializing BertModel 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 BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).

<class 'transformers.models.bert.modeling_bert.BertModel'>
<class 'transformers.models.gpt2.modeling_gpt2.GPT2Model'>

Some weights of the model checkpoint at facebook/bart-base were not used when initializing BartModel: ['final_logits_bias']
- This IS expected if you are initializing BartModel 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 BartModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).

<class 'transformers.models.bart.modeling_bart.BartModel'>

In [ ]:

from transformers import AutoConfig

bert_config = AutoConfig.from_pretrained("bert-base-cased")
print(type(bert_config))

gpt_config = AutoConfig.from_pretrained("gpt2")
print(type(gpt_config))

bart_config = AutoConfig.from_pretrained("facebook/bart-base")
print(type(bart_config))

<class 'transformers.models.bert.configuration_bert.BertConfig'>
<class 'transformers.models.gpt2.configuration_gpt2.GPT2Config'>
<class 'transformers.models.bart.configuration_bart.BartConfig'>

In [ ]:

from transformers import BertConfig

bert_config = BertConfig.from_pretrained("bert-base-cased")
print(type(bert_config))

<class 'transformers.models.bert.configuration_bert.BertConfig'>

In [ ]:

from transformers import GPT2Config

gpt_config = GPT2Config.from_pretrained("gpt2")
print(type(gpt_config))

<class 'transformers.models.gpt2.configuration_gpt2.GPT2Config'>

In [ ]:

from transformers import BartConfig

bart_config = BartConfig.from_pretrained("facebook/bart-base")
print(type(bart_config))

<class 'transformers.models.bart.configuration_bart.BartConfig'>

In [ ]:

from transformers import BertConfig

bert_config = BertConfig.from_pretrained("bert-base-cased")
print(bert_config)

BertConfig {
  "architectures": [
    "BertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "transformers_version": "4.7.0.dev0",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 28996
}

In [ ]:

from transformers import BertConfig, BertModel

bert_config = BertConfig.from_pretrained("bert-base-cased")
bert_model = BertModel(bert_config)

In [ ]:

from transformers import BertConfig, BertModel

bert_config = BertConfig.from_pretrained("bert-base-cased")
bert_model = BertModel(bert_config)

# Training code

bert_model.save_pretrained("my_bert_model")

In [ ]: