upload

CECorrelationEvaluator_sts-dev_results.csv

@@ -0,0 +1,7 @@
+epoch,steps,Pearson_Correlation,Spearman_Correlation
+0,-1,0.8545983323224908,0.8468392535285587
+1,-1,0.8571942532186558,0.8520208839729133
+2,-1,0.8613338704883177,0.8538568557640089
+3,-1,0.8616480884450483,0.8550005160746958
+4,-1,0.8605050883898332,0.8543731967733662
+5,-1,0.8612005934368199,0.8541962412946662

README.md

@@ -0,0 +1,19 @@
+# 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
+This model was trained on the [STS benchmark dataset](http://ixa2.si.ehu.eus/stswiki/index.php/STSbenchmark). The model will predict a score between 0 and 1 how for the semantic similarity of two sentences. 
+
+
+## Usage and Performance
+
+Pre-trained models can be used like this:
+```
+from sentence_transformers import CrossEncoder
+model = CrossEncoder('model_name')
+scores = model.predict([('Sentence 1', 'Sentence 2'), ('Sentence 3', 'Sentence 4')])
+```
+
+The model will predict scores for the pairs `('Sentence 1', 'Sentence 2')` and `('Sentence 3', 'Sentence 4')`.
+
+You can use this model also without sentence_transformers and by just using Transformers ``AutoModel`` class

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "output/TinyBERT_L-4-nli/",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1200,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c81276416deab713ab841b7d4afa2484270d5d23d735d1baa27a7bc1501080e2
+size 57436041

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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": "/home/ukp-reimers/.cache/huggingface/transformers/f96b11e14fec8f4be06121e7f6bbe07f82216bf7d75ad76fe3a81251e8895d69.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "output/TinyBERT_L-4-nli/", "do_basic_tokenize": true, "never_split": null}