julianrisch
commited on
Commit
•
bcf34f8
1
Parent(s):
e3dcd48
FARM model converted to transformers
Browse files- language_model.bin +0 -3
- language_model_config.json +0 -24
- prediction_head_0.bin +0 -3
- prediction_head_0_config.json +0 -1
- processor_config.json +0 -1
- special_tokens_map.json +0 -1
- tokenizer_config.json +0 -1
- vocab.txt +0 -0
language_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:b922923b2684e22849bfe9c1c96314f0879636030b6c792b57521c36b1c7a248
|
3 |
-
size 439797239
|
|
|
|
|
|
|
|
language_model_config.json
DELETED
@@ -1,24 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "deepset/gbert-base",
|
3 |
-
"architectures": [
|
4 |
-
"BertForMaskedLM"
|
5 |
-
],
|
6 |
-
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"gradient_checkpointing": false,
|
8 |
-
"hidden_act": "gelu",
|
9 |
-
"hidden_dropout_prob": 0.1,
|
10 |
-
"hidden_size": 768,
|
11 |
-
"initializer_range": 0.02,
|
12 |
-
"intermediate_size": 3072,
|
13 |
-
"language": "english",
|
14 |
-
"layer_norm_eps": 1e-12,
|
15 |
-
"max_position_embeddings": 512,
|
16 |
-
"model_type": "bert",
|
17 |
-
"name": "Bert",
|
18 |
-
"num_attention_heads": 12,
|
19 |
-
"num_hidden_layers": 12,
|
20 |
-
"pad_token_id": 0,
|
21 |
-
"position_embedding_type": "absolute",
|
22 |
-
"type_vocab_size": 2,
|
23 |
-
"vocab_size": 31102
|
24 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
prediction_head_0.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:73d4cef2f2e15c37228f40fc3c4df48764cb9613a3204b3d715848179937b47e
|
3 |
-
size 7489
|
|
|
|
|
|
|
|
prediction_head_0_config.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"training": false, "layer_dims": [768, 2], "num_labels": 2, "ph_output_type": "per_sequence", "model_type": "text_classification", "task_name": "text_classification", "class_weights": null, "label_tensor_name": "text_classification_label_ids", "label_list": ["0", "1"], "metric": "f1_macro", "name": "TextClassificationHead"}
|
|
|
|
processor_config.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"baskets": [], "data_dir": "../data/ranker", "delimiter": "\t", "dev_filename": "GermanDPR_test.csv", "dev_split": 0.1, "header": 0, "max_samples": null, "max_seq_len": 512, "proxies": null, "quote_char": "'", "skiprows": null, "tasks": {"text_classification": {"label_list": ["0", "1"], "metric": "f1_macro", "label_tensor_name": "text_classification_label_ids", "label_name": "text_classification_label", "label_column_name": "label", "text_column_name": "text", "task_type": "classification"}}, "test_filename": null, "train_filename": "GermanDPR_train.csv", "tokenizer": "BertTokenizerFast", "processor": "TextPairClassificationProcessor"}
|
|
|
|
special_tokens_map.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
|
|
|
tokenizer_config.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "deepset/gbert-base", "do_basic_tokenize": true, "never_split": null}
|
|
|
|
vocab.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|