upload

README.md

@@ -0,0 +1,45 @@
+---
+datasets:
+- squad_v2
+language: en
+license: mit
+pipeline_tag: question-answering
+tags:
+- electra
+- question-answering
+---
+# Electra base model for QA (SQuAD 2.0)
+
+This model uses [electra-base](https://huggingface.co/google/electra-base-discriminator).
+
+## Training Data
+The models have been trained on the [SQuAD 2.0](https://rajpurkar.github.io/SQuAD-explorer/) dataset.
+
+It can be used for question answering task.
+
+## Usage and Performance
+The trained model can be used like this:
+```python
+from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
+
+# Load model & tokenizer
+electra_model = AutoModelForQuestionAnswering.from_pretrained('navteca/electra-base-squad2')
+electra_tokenizer = AutoTokenizer.from_pretrained('navteca/electra-base-squad2')
+
+# Get predictions
+nlp = pipeline('question-answering', model=electra_model, tokenizer=electra_tokenizer)
+
+result = nlp({
+    'question': 'How many people live in Berlin?',
+    'context': 'Berlin had a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.'
+})
+
+print(result)
+
+#{
+#  "answer": "3,520,031"
+#  "end": 36,
+#  "score": 0.99983448,
+#  "start": 27,
+#}
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "ElectraForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "language": "english",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "name": "Electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33abdbab680c8bae8707320df17c5d4fba5969adb465e81029905fa0284d3d3e
+size 435618605

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+    "cls_token": "[CLS]",
+    "mask_token": "[MASK]",
+    "pad_token": "[PAD]",
+    "sep_token": "[SEP]",
+    "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+    "do_basic_tokenize": true,
+    "do_lower_case": true,
+    "model_max_length": 512,
+    "never_split": null,
+    "special_tokens_map_file": "special_tokens_map.json",
+    "strip_accents": null,
+    "tokenize_chinese_chars": true
+}