up

CESoftmaxAccuracyEvaluator_AllNLI-dev_results.csv

@@ -0,0 +1,13 @@
+epoch,steps,Accuracy
+0,10000,0.8647301215851859
+0,20000,0.8722083736073664
+0,30000,0.8845195095894592
+0,40000,0.8869105153380475
+0,50000,0.8886910515338048
+0,-1,0.8922521239253193
+1,10000,0.8953553441522104
+1,20000,0.8956605789286259
+1,30000,0.898204202065422
+1,40000,0.9005443353512743
+1,50000,0.9018670193824083
+1,-1,0.9018670193824083

README.md

@@ -0,0 +1,38 @@
+# Cross-Encoder for Quora Duplicate Questions Detection
+This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class.
+
+## Training Data
+The model was trained on the [SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral.
+
+
+## Usage
+
+Pre-trained models can be used like this:
+```python
+from sentence_transformers import CrossEncoder
+model = CrossEncoder('model_name')
+scores = model.predict([('A man is eating pizza', 'A man eats something'), ('A black race car starts up in front of a crowd of people.', 'A man is driving down a lonely road.')])
+
+#Convert scores to labels
+label_mapping = ['contradiction', 'entailment', 'neutral']
+labels = [label_mapping[score_max] for score_max in scores.argmax(axis=1)]
+```
+
+## Usage with Transformers AutoModel
+You can use the model also directly with Transformers library (without SentenceTransformers library):
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+model = AutoModelForSequenceClassification.from_pretrained('model_name')
+tokenizer = AutoTokenizer.from_pretrained('model_name')
+
+features = tokenizer(['A man is eating pizza', 'A black race car starts up in front of a crowd of people.'], ['A man eats something', 'A man is driving down a lonely road.'],  padding=True, truncation=True, return_tensors="pt")
+
+model.eval()
+with torch.no_grad():
+    scores = model(**features).logits
+    label_mapping = ['contradiction', 'entailment', 'neutral']
+    labels = [label_mapping[score_max] for score_max in scores.argmax(dim=1)]
+    print(labels)
+```

bpe_encoder.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caff5a98d15fd439255194f3fcfd41a7b276b500cdf69caba890ae242c498797
+size 3918127

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "microsoft/deberta-base",
+  "architectures": [
+    "DebertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ef040f1fba1b3ff1916e2dd02b3d73d161dd085907e5181ef26261d65df69f
+size 556869824

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]", "model_max_length": 512, "name_or_path": "microsoft/deberta-base"}