初始化项目，由ModelHub XC社区提供模型

Model: Sahajtomar/German-semantic
Source: Original Platform

.gitattributes

@@ -0,0 +1,16 @@
+*.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
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text

0_Transformer/config.json

@@ -0,0 +1,21 @@
+{
+  "_name_or_path": "deepset/gbert-large",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "type_vocab_size": 2,
+  "vocab_size": 31102
+}

0_Transformer/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d4ef74fe3c2aa5db17ab32fc97f94adefc5e4d9e34203b620a59c6d1047aae
+size 1343042635

0_Transformer/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": null,
+  "do_lower_case": false
+}

0_Transformer/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

0_Transformer/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]", "tokenize_chinese_chars": true, "strip_accents": false, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "deepset/gbert-large", "do_basic_tokenize": true, "never_split": null}

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,47 @@
+---
+language: de
+tags:
+- semantic
+- sentence-transformers
+- sentence-similarity
+datasets:
+- sts
+---
+# German STS
+
+## STS dev (german)
+87.9%
+## STS test (german)
+84.3%
+
+#### STS pipeline
+```python
+
+!pip install -U sentence-transformers
+from sentence_transformers import SentenceTransformer
+model = SentenceTransformer('..model_path..')
+sentences1 = ['Die Katze sitzt draußen',
+             "Ein Mann spielt Gitarre",
+             'Der neue Film ist großartig']
+
+sentences2 = ['Der Hund spielt im Garten',
+              "Eine Frau sieht fern",
+              'Der neue Film ist so toll']
+embeddings1 = model.encode(sentences1, convert_to_tensor=True)
+embeddings2 = model.encode(sentences2, convert_to_tensor=True)
+cosine_scores = util.pytorch_cos_sim(embeddings1, embeddings2)
+
+for i in range(len(sentences1)):
+    for j in range(len(sentences2)):
+        print(cosine_scores[i][j]))
+"""
+Die Katze sitzt draußen  Der Hund spielt im Garten  Score: 0.1259
+Die Katze sitzt draußen  Eine Frau sieht fern Score: 0.0567
+Die Katze sitzt draußen  Der neue Film ist so toll Score: 0.0557
+Ein Mann spielt Gitarre  Der Hund spielt im Garten  Score: 0.1031
+Ein Mann spielt Gitarre  Eine Frau sieht fern Score: 0.0098
+Ein Mann spielt Gitarre  Der neue Film ist so toll  Score: 0.0828
+Der neue Film ist großartig Der Hund spielt im Garten  Score: 0.1008
+Der neue Film ist großartig Eine Frau sieht fern  Score: 0.0674
+""" 
+```

config.json

@@ -0,0 +1,4 @@
+{
+  "__version__": "1.0.4",
+  "model_type": "bert"
+}

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "0_Transformer",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]