Instructions to use patrickvonplaten/bert2bert-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use patrickvonplaten/bert2bert-tiny with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("patrickvonplaten/bert2bert-tiny") model = AutoModelForSeq2SeqLM.from_pretrained("patrickvonplaten/bert2bert-tiny", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 3,332 Bytes
51cb1ca 0406eac 51cb1ca 0406eac 51cb1ca 0406eac 51cb1ca 0406eac 51cb1ca d59e99d 0e9a3af 0406eac | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 | {
"architectures": [
"EncoderDecoderModel"
],
"decoder": {
"add_cross_attention": true,
"architectures": null,
"attention_probs_dropout_prob": 0.1,
"bad_words_ids": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"decoder_start_token_id": null,
"do_sample": false,
"early_stopping": false,
"eos_token_id": null,
"finetuning_task": null,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 128,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 512,
"is_decoder": true,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 512,
"min_length": 0,
"model_type": "bert",
"no_repeat_ngram_size": 0,
"num_attention_heads": 2,
"num_beams": 1,
"num_hidden_layers": 2,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 0,
"prefix": null,
"pruned_heads": {},
"repetition_penalty": 1.0,
"return_dict": false,
"sep_token_id": null,
"task_specific_params": null,
"temperature": 1.0,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"type_vocab_size": 2,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 30522,
"xla_device": null
},
"encoder": {
"add_cross_attention": false,
"architectures": null,
"attention_probs_dropout_prob": 0.1,
"bad_words_ids": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"decoder_start_token_id": null,
"do_sample": false,
"early_stopping": false,
"eos_token_id": null,
"finetuning_task": null,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 128,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 512,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 512,
"min_length": 0,
"model_type": "bert",
"no_repeat_ngram_size": 0,
"num_attention_heads": 2,
"num_beams": 1,
"num_hidden_layers": 2,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 0,
"prefix": null,
"pruned_heads": {},
"repetition_penalty": 1.0,
"return_dict": false,
"sep_token_id": null,
"task_specific_params": null,
"temperature": 1.0,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"type_vocab_size": 2,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 30522,
"xla_device": null
},
"is_encoder_decoder": true,
"model_type": "encoder-decoder",
"tie_encoder_decoder": true,
"vocab_size": 30522
}
|