upload

.gitattributes

@@ -20,7 +20,6 @@
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
@@ -29,3 +28,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,86 @@
+---
+datasets:
+- squad_v2
+language: en
+license: mit
+pipeline_tag: question-answering
+tags:
+- deberta
+- deberta-v3
+model-index:
+- name: navteca/deberta-v3-base-squad2
+  results:
+  - task:
+      type: question-answering
+      name: Question Answering
+    dataset:
+      name: squad_v2
+      type: squad_v2
+      config: squad_v2
+      split: validation
+    metrics:
+    - name: Exact Match
+      type: exact_match
+      value: 88.0876
+      verified: true
+    - name: F1
+      type: f1
+      value: 91.1623
+      verified: true
+  - task:
+      type: question-answering
+      name: Question Answering
+    dataset:
+      name: squad
+      type: squad
+      config: plain_text
+      split: validation
+    metrics:
+    - name: Exact Match
+      type: exact_match
+      value: 89.2366
+      verified: true
+    - name: F1
+      type: f1
+      value: 95.0569
+      verified: true
+---
+
+# Deberta v3 large model for QA (SQuAD 2.0)
+
+This is the [deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) model, fine-tuned using the [SQuAD2.0](https://huggingface.co/datasets/squad_v2) dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Question Answering.
+
+## 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
+deberta_model = AutoModelForQuestionAnswering.from_pretrained('navteca/deberta-v3-large-squad2')
+deberta_tokenizer = AutoTokenizer.from_pretrained('navteca/deberta-v3-large-squad2')
+
+# Get predictions
+nlp = pipeline('question-answering', model=deberta_model, tokenizer=deberta_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,
+#}
+```
+
+## Author
+[deepset](http://deepset.ai/)

added_tokens.json

@@ -0,0 +1,3 @@
+{
+    "[MASK]": 128000
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "DebertaV2ForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "language": "english",
+  "layer_norm_eps": 1e-7,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "name": "DebertaV2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "summary_activation": "tanh",
+  "summary_last_dropout": 0,
+  "summary_type": "first",
+  "summary_use_proj": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc31220db2ad55672fea1f369664c17628c021b528b1ae65b4b3f2bc7c6910e4
+size 1736194351

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+    "bos_token": "[CLS]",
+    "cls_token": "[CLS]",
+    "eos_token": "[SEP]",
+    "mask_token": "[MASK]",
+    "pad_token": "[PAD]",
+    "sep_token": "[SEP]",
+    "unk_token": "[UNK]"
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+    "bos_token": "[CLS]",
+    "cls_token": "[CLS]",
+    "do_lower_case": false,
+    "eos_token": "[SEP]",
+    "mask_token": "[MASK]",
+    "pad_token": "[PAD]",
+    "sep_token": "[SEP]",
+    "sp_model_kwargs": {},
+    "special_tokens_map_file": null,
+    "split_by_punct": false,
+    "tokenizer_class": "DebertaV2Tokenizer",
+    "unk_token": "[UNK]",
+    "vocab_type": "spm"
+}