初始化项目,由ModelHub XC社区提供模型
Model: cross-encoder/stsb-roberta-base Source: Original Platform
This commit is contained in:
10
.gitattributes
vendored
Normal file
10
.gitattributes
vendored
Normal file
@@ -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
|
||||
7
CECorrelationEvaluator_sts-dev_results.csv
Normal file
7
CECorrelationEvaluator_sts-dev_results.csv
Normal file
@@ -0,0 +1,7 @@
|
||||
epoch,steps,Pearson_Correlation,Spearman_Correlation
|
||||
0,-1,0.884083449570549,0.8863177324254378
|
||||
1,-1,0.9005634047434494,0.8979486190100184
|
||||
2,-1,0.9025966516139985,0.8991112912317778
|
||||
3,-1,0.9027764763549494,0.8998067524459462
|
||||
4,-1,0.9030718202264396,0.9010020546460012
|
||||
5,-1,0.9041287939833499,0.9017253433578207
|
||||
|
33
README.md
Normal file
33
README.md
Normal file
@@ -0,0 +1,33 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- sentence-transformers/stsb
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- FacebookAI/roberta-base
|
||||
pipeline_tag: text-ranking
|
||||
library_name: sentence-transformers
|
||||
tags:
|
||||
- transformers
|
||||
---
|
||||
# Cross-Encoder for Semantic Textual Similarity
|
||||
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:
|
||||
```python
|
||||
from sentence_transformers import CrossEncoder
|
||||
|
||||
model = CrossEncoder('cross-encoder/stsb-roberta-base')
|
||||
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
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -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
|
||||
}
|
||||
3
flax_model.msgpack
Normal file
3
flax_model.msgpack
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:768905d4b87ebefec4c819d9a36518802db21df7fc2d9e8ce7cb47ed3875283f
|
||||
size 498592825
|
||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:130e4eac117036a5803c3f832e95185b558d341cb9c4e576975614d8b1340ef7
|
||||
size 498613948
|
||||
3
onnx/model.onnx
Normal file
3
onnx/model.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c82166bb8dc6c022fb94e8aa7e7b0af4240cbfcbf8f29a58a5d26dcac5146711
|
||||
size 498905040
|
||||
3
onnx/model_O1.onnx
Normal file
3
onnx/model_O1.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2c1d4fdfa85014dc12cf3cffd1ec7e63bee02c0c93ac17d0181732b68112b9b7
|
||||
size 498803421
|
||||
3
onnx/model_O2.onnx
Normal file
3
onnx/model_O2.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ae90e2d6fd8ab7708d2a857cc8d73df004ac5547ddec0babbb1288e2fb0e4baa
|
||||
size 498626418
|
||||
3
onnx/model_O3.onnx
Normal file
3
onnx/model_O3.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6ff18d82c77ea2c1c63aefab366c334bd1fe122626cdacd12c375114eba7d5ec
|
||||
size 498626273
|
||||
3
onnx/model_O4.onnx
Normal file
3
onnx/model_O4.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:82678eb4507e362812e44a803a7f2d3849f58f03ae22035e3fc4b6c3c45ed99c
|
||||
size 249470678
|
||||
3
onnx/model_qint8_arm64.onnx
Normal file
3
onnx/model_qint8_arm64.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8b44d8ffa6775a7712e9f592b8a33162b3c183fedaeb2399bd0e2e40a5ddbd16
|
||||
size 126017827
|
||||
3
onnx/model_qint8_avx512.onnx
Normal file
3
onnx/model_qint8_avx512.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8b44d8ffa6775a7712e9f592b8a33162b3c183fedaeb2399bd0e2e40a5ddbd16
|
||||
size 126017827
|
||||
3
onnx/model_qint8_avx512_vnni.onnx
Normal file
3
onnx/model_qint8_avx512_vnni.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8b44d8ffa6775a7712e9f592b8a33162b3c183fedaeb2399bd0e2e40a5ddbd16
|
||||
size 126017827
|
||||
3
onnx/model_quint8_avx2.onnx
Normal file
3
onnx/model_quint8_avx2.onnx
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ecca55ec425a68accbb9796cf65351332d9e5cdb42a291f66a90b6e9dffd38ce
|
||||
size 126017824
|
||||
3
openvino/openvino_model.bin
Normal file
3
openvino/openvino_model.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4153ca3905be859cb0d13e718fdf31413c569b00a0c3f7b3875f485377921bca
|
||||
size 498589876
|
||||
12477
openvino/openvino_model.xml
Normal file
12477
openvino/openvino_model.xml
Normal file
File diff suppressed because it is too large
Load Diff
3
openvino/openvino_model_qint8_quantized.bin
Normal file
3
openvino/openvino_model_qint8_quantized.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fc01458a7eef642064bbefbc7c84f867b3eaec921468520821332f428e7dad21
|
||||
size 125819768
|
||||
21421
openvino/openvino_model_qint8_quantized.xml
Normal file
21421
openvino/openvino_model_qint8_quantized.xml
Normal file
File diff suppressed because it is too large
Load Diff
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bd8cddb9f6ddf924f91a1cc3c2bf83973a483a936654259d389ed1e7c56711d2
|
||||
size 498676169
|
||||
51
special_tokens_map.json
Normal file
51
special_tokens_map.json
Normal file
@@ -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
|
||||
}
|
||||
}
|
||||
250357
tokenizer.json
Normal file
250357
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
59
tokenizer_config.json
Normal file
59
tokenizer_config.json
Normal file
@@ -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>"
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user