Update tiny models for EncoderDecoderModel-bert-bert
Browse files- config.json +95 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
config.json
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"EncoderDecoderModel"
|
| 4 |
+
],
|
| 5 |
+
"decoder": {
|
| 6 |
+
"_name_or_path": "/tmp/tmpk7yofmau/decoder/BertLMHeadModel",
|
| 7 |
+
"add_cross_attention": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"BertLMHeadModel"
|
| 10 |
+
],
|
| 11 |
+
"attention_probs_dropout_prob": 0.1,
|
| 12 |
+
"bos_token_id": null,
|
| 13 |
+
"chunk_size_feed_forward": 0,
|
| 14 |
+
"classifier_dropout": null,
|
| 15 |
+
"dtype": "float32",
|
| 16 |
+
"eos_token_id": null,
|
| 17 |
+
"hidden_act": "gelu",
|
| 18 |
+
"hidden_dropout_prob": 0.1,
|
| 19 |
+
"hidden_size": 32,
|
| 20 |
+
"id2label": {
|
| 21 |
+
"0": "LABEL_0",
|
| 22 |
+
"1": "LABEL_1"
|
| 23 |
+
},
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 37,
|
| 26 |
+
"is_decoder": true,
|
| 27 |
+
"is_encoder_decoder": false,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"LABEL_0": 0,
|
| 30 |
+
"LABEL_1": 1
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-12,
|
| 33 |
+
"max_position_embeddings": 512,
|
| 34 |
+
"model_type": "bert",
|
| 35 |
+
"num_attention_heads": 4,
|
| 36 |
+
"num_hidden_layers": 2,
|
| 37 |
+
"output_attentions": false,
|
| 38 |
+
"output_hidden_states": false,
|
| 39 |
+
"pad_token_id": 0,
|
| 40 |
+
"problem_type": null,
|
| 41 |
+
"return_dict": true,
|
| 42 |
+
"tie_word_embeddings": true,
|
| 43 |
+
"type_vocab_size": 16,
|
| 44 |
+
"use_cache": true,
|
| 45 |
+
"vocab_size": 30522
|
| 46 |
+
},
|
| 47 |
+
"decoder_start_token_id": null,
|
| 48 |
+
"dtype": "float32",
|
| 49 |
+
"encoder": {
|
| 50 |
+
"_name_or_path": "/tmp/tmpk7yofmau/encoder/BertModel",
|
| 51 |
+
"add_cross_attention": false,
|
| 52 |
+
"architectures": [
|
| 53 |
+
"BertModel"
|
| 54 |
+
],
|
| 55 |
+
"attention_probs_dropout_prob": 0.1,
|
| 56 |
+
"bos_token_id": null,
|
| 57 |
+
"chunk_size_feed_forward": 0,
|
| 58 |
+
"classifier_dropout": null,
|
| 59 |
+
"dtype": "float32",
|
| 60 |
+
"eos_token_id": null,
|
| 61 |
+
"hidden_act": "gelu",
|
| 62 |
+
"hidden_dropout_prob": 0.1,
|
| 63 |
+
"hidden_size": 32,
|
| 64 |
+
"id2label": {
|
| 65 |
+
"0": "LABEL_0",
|
| 66 |
+
"1": "LABEL_1"
|
| 67 |
+
},
|
| 68 |
+
"initializer_range": 0.02,
|
| 69 |
+
"intermediate_size": 37,
|
| 70 |
+
"is_decoder": false,
|
| 71 |
+
"is_encoder_decoder": false,
|
| 72 |
+
"label2id": {
|
| 73 |
+
"LABEL_0": 0,
|
| 74 |
+
"LABEL_1": 1
|
| 75 |
+
},
|
| 76 |
+
"layer_norm_eps": 1e-12,
|
| 77 |
+
"max_position_embeddings": 512,
|
| 78 |
+
"model_type": "bert",
|
| 79 |
+
"num_attention_heads": 4,
|
| 80 |
+
"num_hidden_layers": 2,
|
| 81 |
+
"output_attentions": false,
|
| 82 |
+
"output_hidden_states": false,
|
| 83 |
+
"pad_token_id": 0,
|
| 84 |
+
"problem_type": null,
|
| 85 |
+
"return_dict": true,
|
| 86 |
+
"tie_word_embeddings": true,
|
| 87 |
+
"type_vocab_size": 16,
|
| 88 |
+
"use_cache": true,
|
| 89 |
+
"vocab_size": 30522
|
| 90 |
+
},
|
| 91 |
+
"is_encoder_decoder": true,
|
| 92 |
+
"model_type": "encoder-decoder",
|
| 93 |
+
"pad_token_id": null,
|
| 94 |
+
"transformers_version": "5.16.0.dev0"
|
| 95 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"output_attentions": false,
|
| 4 |
+
"output_hidden_states": false,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "5.16.0.dev0",
|
| 7 |
+
"use_cache": true
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e65841a2c71445402e2360211458524bb408076242bed24590b9d8a56830ad5
|
| 3 |
+
size 8234960
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": true,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|