Our first big model!

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "deepset/gelectra-large-germanquad",
+  "architectures": [
+    "ElectraForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 1024,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "language": "german",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "name": "Electra",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0,
+  "summary_type": "first",
+  "summary_use_proj": false,
+  "transformers_version": "4.13.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

prediction_head_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5daa727ba926904765f3f462479c48b48de06f66bd4f792a727778fae6b4e7e
+size 9635

prediction_head_0_config.json

@@ -0,0 +1 @@
+{"training": true, "layer_dims": [1024, 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

@@ -0,0 +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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf03db761198296a4ec837505cc2779a53155cee0b79c9e15868e02ff501c46
+size 1338900981

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -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/gelectra-large-germanquad", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}