初始化项目，由ModelHub XC社区提供模型

Model: cross-encoder/quora-roberta-base
Source: Original Platform

.gitattributes

@@ -0,0 +1,10 @@
+*.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
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

CEBinaryClassificationEvaluator_Quora-dev_results.csv

@@ -0,0 +1,15 @@
+epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average_Precision
+0,5000,0.8608639203700198,0.2873433232307434,0.8098558473933306,0.19083455204963684,0.7614130434782609,0.8648815495022764,0.8629331317298123
+0,10000,0.863839225338779,0.25037556886672974,0.8119228437979106,0.12073762714862823,0.7546394485683987,0.8786171772513311,0.8678734374248867
+0,15000,0.8680587487490194,0.2262679636478424,0.8200071968333933,0.11036892235279083,0.7682556806688693,0.8792345088355583,0.875549687970233
+0,20000,0.8685456168348165,0.20787009596824646,0.8190316830962862,0.12376940995454788,0.7747041012936967,0.8687398719036963,0.8764299796079794
+0,25000,0.8720077898893728,0.3845294713973999,0.8250813155041562,0.2559159994125366,0.7759499694106451,0.8808550042441546,0.8833998414872404
+0,30000,0.8729815260609667,0.5238280296325684,0.8255852051403401,0.3320024907588959,0.781461061337009,0.8749903541939964,0.878249009917573
+0,-1,0.8710611019447675,0.4382350444793701,0.8225952648562416,0.149741068482399,0.7758172616605116,0.8753761864341384,0.8821009813520877
+1,5000,0.8723864650672148,0.13579325377941132,0.8250017981730562,0.046766698360443115,0.772546642419344,0.8850991588857164,0.8772769680139632
+1,10000,0.8706012820859592,0.17663632333278656,0.8243606757289911,0.04282882809638977,0.7701380511995711,0.8867968207423412,0.8717299987211413
+1,15000,0.8711963430797112,0.062239423394203186,0.8229883392482075,0.025501983240246773,0.775366769020812,0.876842348946678,0.88006993940756
+1,20000,0.8719266452084066,0.03155897557735443,0.8244302380178423,0.010280131362378597,0.7749185225420967,0.8807006713480978,0.8812910141874843
+1,25000,0.8726028508831246,0.03645790368318558,0.8253768844221104,0.03082387149333954,0.7918468628146047,0.8618720580291689,0.8816145619414946
+1,30000,0.8732249601038652,0.03989178314805031,0.8268535595721136,0.029114533215761185,0.7920288318846724,0.8648815495022764,0.8793008086700131
+1,-1,0.8735765870547185,0.05718168243765831,0.8270970543533329,0.018996555358171463,0.7787393526405452,0.8818581680685238,0.8779853764105872

README.md

@@ -0,0 +1,32 @@
+---
+license: apache-2.0
+datasets:
+- sentence-transformers/quora-duplicates
+language:
+- en
+base_model:
+- FacebookAI/roberta-base
+pipeline_tag: text-ranking
+library_name: sentence-transformers
+tags:
+- transformers
+---
+# 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 [Quora Duplicate Questions](https://www.quora.com/q/quoradata/First-Quora-Dataset-Release-Question-Pairs) dataset. The model will predict a score between 0 and 1 how likely the two given questions are duplicates.
+
+Note: The model is not suitable to estimate the similarity of questions, e.g. the two questions "How to learn Java" and "How to learn Python" will result in a rather low score, as these are not duplicates.
+
+## Usage and Performance
+
+Pre-trained models can be used like this:
+```python
+from sentence_transformers import CrossEncoder
+
+model = CrossEncoder('cross-encoder/quora-roberta-base')
+scores = model.predict([('Question 1', 'Question 2'), ('Question 3', 'Question 4')])
+```
+
+You can use this model also without sentence_transformers and by just using Transformers ``AutoModel`` class

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e3f35ee5fa4bbd55ddee08e12bdbe19fcec65d978d5df08bccacd206964e4f
+size 498592825

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:746da6a97a533563fac5862d54b20fe24550c3e43672ab086542cd17c18f9148
+size 498613948

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d46af47d58e81400db15a553fed543bd1b02a3ebba6cdf194a0c6ced6714cb
+size 498905040

onnx/model_O1.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3015194265815fa638a7339afa9ae888c6e38d69f1b711698f1b894e2bcc109f
+size 498803421

onnx/model_O2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f897eac0ad72f28674212d04c607d33cf85f63d8240d60a643a94e3e31555a73
+size 498626418

onnx/model_O3.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7772a18043c86686b1c862c7bece1274f73f2e5cea1af74f24c25dc6cce80d3
+size 498626273

onnx/model_O4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c753d011621d622a6afa18c173779d9f4ad1de5ec8801493ee6edfe93c0297
+size 249470678

onnx/model_qint8_arm64.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11ae2b71d9c51757c6842582352dbba3757dc56ca7ecaad09137250c59352a5
+size 126017827

onnx/model_qint8_avx512.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11ae2b71d9c51757c6842582352dbba3757dc56ca7ecaad09137250c59352a5
+size 126017827

onnx/model_qint8_avx512_vnni.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11ae2b71d9c51757c6842582352dbba3757dc56ca7ecaad09137250c59352a5
+size 126017827

onnx/model_quint8_avx2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f483440ba8e675c2d152249374a5537fa04f30a5564ae5c0f50c479ab3e280e6
+size 126017824

openvino/openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f89c2a8f546aad6d4b6cf36000112e5e7d5921a6799f6dd502739e1bfa6b9409
+size 498589876

openvino/openvino_model_qint8_quantized.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d5819f8e13bf7d32b2bd6c8206a3d5852eb36ba4c3207406f201e5036ca469
+size 125819768

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbebb63aa533e7d3b68b2e0d205287523fff83ab36e434003d55f855e699acc6
+size 498676169

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "full_tokenizer_file": null,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}