初始化项目,由ModelHub XC社区提供模型

Model: cross-encoder/stsb-roberta-large
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-13 17:27:21 +08:00
commit 38514fdb31
25 changed files with 365758 additions and 0 deletions

10
.gitattributes vendored Normal file
View 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

View File

@@ -0,0 +1,5 @@
epoch,steps,Pearson_Correlation,Spearman_Correlation
0,-1,0.9169803189330423,0.914689659080599
1,-1,0.9184629642176918,0.9145474423018756
2,-1,0.9140695557809773,0.911543895130673
3,-1,0.9156662483528688,0.9134139344421147
1 epoch steps Pearson_Correlation Spearman_Correlation
2 0 -1 0.9169803189330423 0.914689659080599
3 1 -1 0.9184629642176918 0.9145474423018756
4 2 -1 0.9140695557809773 0.911543895130673
5 3 -1 0.9156662483528688 0.9134139344421147

33
README.md Normal file
View File

@@ -0,0 +1,33 @@
---
license: apache-2.0
datasets:
- sentence-transformers/stsb
language:
- en
base_model:
- FacebookAI/roberta-large
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-large')
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

29
config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"_num_labels": 3,
"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": 1024,
"id2label": {
"0": "LABEL_0"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"LABEL_0": 0
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "roberta",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 1,
"type_vocab_size": 1,
"vocab_size": 50265
}

3
flax_model.msgpack Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:646b3fe48a91743c4bfd18fa129ee4278573dd6634324e64baa6d8b7104c11ef
size 1421457127

50001
merges.txt Normal file

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:613af2a4f0a5deb23b07c71649c50a1e1cd76470697f3104e11a7859d80ca832
size 1421495516

3
onnx/model.onnx Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b26274ff04219b5bcc8e09202205201d0e9bfb8905d02c5cb9d2e133f229d55c
size 1422070180

3
onnx/model_O1.onnx Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bee5a8a1f6db9ffb7fb0a5d8fe0c0cb8c4e204dfa907a0beac4884dc70352e5e
size 1421867443

3
onnx/model_O2.onnx Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2cdde759506204305ec7426647f8c2b16d6c7ea5ecfe23b1f573a634c96dee43
size 1421515824

3
onnx/model_O3.onnx Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:40fd080a90f9195f94c8b89b1a83798ae5972408acb447b159931f099d5d27e2
size 1421515535

3
onnx/model_O4.onnx Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7a03bde92ae3ec5d11fd57e9f63210d7f1e198800b55ea6e5b39ad93530e68f4
size 711066308

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e015610e2454296350ebd3b1c0e12646075066734c628c40648fc6796073d9d7
size 358595116

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e015610e2454296350ebd3b1c0e12646075066734c628c40648fc6796073d9d7
size 358595116

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e015610e2454296350ebd3b1c0e12646075066734c628c40648fc6796073d9d7
size 358595116

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c1daad07e40faf372bbca890456a5b4b1a3422223aaea916c4c2ba961c42a843
size 358595114

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:caeed3fdd51245b064b8ba14dfa5582083b5379ddb1b4d47568e34dbb9e5d11d
size 1421447348

23841
openvino/openvino_model.xml Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9592b5aeb6e340c9648e0769a84cd2a0d9d4c60dc5b9646fa500b5838f4f7dc6
size 358122168

File diff suppressed because it is too large Load Diff

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:03023f7dcd714c15ff27d534432a80d3bff78c9b50778a44b10585ef5fa7fd25
size 1421616585

51
special_tokens_map.json Normal file
View 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

File diff suppressed because it is too large Load Diff

59
tokenizer_config.json Normal file
View 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

File diff suppressed because one or more lines are too long