Commit ·
2d26657
1
Parent(s): 3cb6bd4
First commit!
Browse files- config.json +31 -0
- prediction_head_0.bin +3 -0
- prediction_head_0_config.json +1 -0
- processor_config.json +1 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepset/gelectra-base-germanquad",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ElectraForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"embedding_size": 768,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"language": "german",
|
| 15 |
+
"layer_norm_eps": 1e-12,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"model_type": "electra",
|
| 18 |
+
"name": "Electra",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"summary_activation": "gelu",
|
| 24 |
+
"summary_last_dropout": 0,
|
| 25 |
+
"summary_type": "first",
|
| 26 |
+
"summary_use_proj": false,
|
| 27 |
+
"transformers_version": "4.13.0",
|
| 28 |
+
"type_vocab_size": 2,
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 31102
|
| 31 |
+
}
|
prediction_head_0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69ab4e6ea3bbb7670fbcf11df58f2f9dbb7de945c1b823294deffb2c0d7cf044
|
| 3 |
+
size 7587
|
prediction_head_0_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"training": true, "layer_dims": [768, 2], "num_labels": 2, "ph_output_type": "per_token_squad", "model_type": "span_classification", "task_name": "question_answering", "no_ans_boost": 0.0, "context_window_size": 150, "n_best": 4, "n_best_per_sample": 1, "duplicate_filtering": 0, "use_confidence_scores_for_ranking": false, "label_tensor_name": "question_answering_label_ids", "label_list": ["start_token", "end_token"], "metric": "squad", "name": "QuestionAnsweringHead"}
|
processor_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"baskets": [], "data_dir": "data", "dev_filename": "dev-v2.0.json", "dev_split": 0, "doc_stride": 128, "max_answers": 6, "max_query_length": 64, "max_seq_len": 256, "multithreading_rust": true, "ph_output_type": "per_token_squad", "proxies": null, "sp_toks_end": 1, "sp_toks_mid": 1, "sp_toks_start": 1, "tasks": {"question_answering": {"label_list": ["start_token", "end_token"], "metric": "squad", "label_tensor_name": "question_answering_label_ids", "label_name": "question_answering_label", "label_column_name": null, "text_column_name": null, "task_type": null}}, "test_filename": null, "train_filename": "train-v2.0.json", "tokenizer": "ElectraTokenizerFast", "processor": "SquadProcessor"}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:910b7360cadf0aa0e32ff68e8814e3bc01bfe7f80191e0c70bbee6271c1d9d01
|
| 3 |
+
size 437428981
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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/gelectra-base-germanquad", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|