upload

.gitattributes

@@ -1,16 +1,17 @@
-*.bin.* filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tar.gz filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,45 @@
+---
+datasets:
+- squad_v2
+language: en
+license: mit
+pipeline_tag: question-answering
+tags:
+- roberta
+- question-answering
+---
+# Roberta large model for QA (SQuAD 2.0)
+
+This model uses [roberta-large](https://huggingface.co/roberta-large).
+
+## 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
+roberta_model = AutoModelForQuestionAnswering.from_pretrained('navteca/roberta-large-squad2')
+roberta_tokenizer = AutoTokenizer.from_pretrained('navteca/roberta-large-squad2')
+
+# Get predictions
+nlp = pipeline('question-answering', model=roberta_model, tokenizer=roberta_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": 0.96186668,
+#  "start": 27,
+#}
+```

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "language": "english",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "name": "Roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d19dd0f99103b4278204f0b76f680e8ae6be57586ead9c5e4291d1a553b0cd
+size 1417262751

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a98cec67b9022abbcc667656745dd04a87e2c56d07d8f5175df22b09f90fc5
+size 1417415991

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+    "bos_token": {
+        "content": "<s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "eos_token": {
+        "content": "</s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "unk_token": {
+        "content": "<unk>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "sep_token": {
+        "content": "</s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "pad_token": {
+        "content": "<pad>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "cls_token": {
+        "content": "<s>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true
+    },
+    "mask_token": {
+        "content": "<mask>",
+        "single_word": false,
+        "lstrip": true,
+        "rstrip": false,
+        "normalized": true
+    }
+}

tokenizer_config.json

@@ -0,0 +1,6 @@
+{
+    "do_lower_case": false,
+    "full_tokenizer_file": null,
+    "model_max_length": 512,
+    "special_tokens_map_file": "special_tokens_map.json"
+}