初始化项目，由ModelHub XC社区提供模型

Model: khanhpd2/sbert_phobert_large_cosine_sim
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

1_Pooling.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08df6211b345a7289f908fb5bd12628c000a75cdf5a7cbf6abff5d81e37f583b
+size 480

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "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 +1,126 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
+model = AutoModel.from_pretrained('{MODEL_NAME}')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 1304 with parameters:
+```
+{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 30,
+    "evaluation_steps": 1304,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 3912,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: RobertaModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "neurondbert-finetuned-squad2",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.24.0",
+    "pytorch": "1.12.1+cu113"
+  }
+}

eval/similarity_evaluation_results.csv

@@ -0,0 +1,57 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,1304,-0.956252173016181,-0.5,-0.9395408012001706,-0.5,-0.9465085070741878,-0.5,-0.986590422554226,-1.0
+0,-1,-0.956252173016181,-0.5,-0.9395408012001706,-0.5,-0.9465085070741878,-0.5,-0.986590422554226,-1.0
+1,1304,-0.7502727155089846,-1.0,-0.26299886114524607,-0.5,-0.13723091250119945,-0.5,-0.9766641134673515,-1.0
+1,-1,-0.7502727155089846,-1.0,-0.26299886114524607,-0.5,-0.13723091250119945,-0.5,-0.9766641134673515,-1.0
+2,1304,0.23241596979461562,-0.5,0.40769864546562196,0.5,0.4252709403985148,0.5,-0.17724551444561853,-0.5
+2,-1,0.23241596979461562,-0.5,0.40769864546562196,0.5,0.4252709403985148,0.5,-0.17724551444561853,-0.5
+3,1304,0.233054750394314,-0.5,0.46878018654359743,0.5,0.4694324475423289,0.5,-0.375561520632018,-0.5
+3,-1,0.233054750394314,-0.5,0.46878018654359743,0.5,0.4694324475423289,0.5,-0.375561520632018,-0.5
+4,1304,0.3700546533092378,0.5,0.5373617608166298,0.5,0.5449287777333985,0.5,-0.32815770480773654,-0.5
+4,-1,0.3700546533092378,0.5,0.5373617608166298,0.5,0.5449287777333985,0.5,-0.32815770480773654,-0.5
+5,1304,-0.06639210366879778,-0.5,0.3846954043812294,0.5,0.40143797079279175,0.5,-0.8499838376151696,-1.0
+5,-1,-0.06639210366879778,-0.5,0.3846954043812294,0.5,0.40143797079279175,0.5,-0.8499838376151696,-1.0
+6,1304,-0.09594551657615569,-0.5,0.2657556783662266,-0.5,0.19574241451070368,-0.5,-0.8621859504816876,-1.0
+6,-1,-0.09594551657615569,-0.5,0.2657556783662266,-0.5,0.19574241451070368,-0.5,-0.8621859504816876,-1.0
+7,1304,-0.20563168280352673,-0.5,0.29022823195252273,0.5,0.2995270383361658,0.5,-0.8933937248046327,-0.5
+7,-1,-0.20563168280352673,-0.5,0.29022823195252273,0.5,0.2995270383361658,0.5,-0.8933937248046327,-0.5
+8,1304,0.990887513427043,1.0,0.9968673446294058,1.0,0.9998512199273387,1.0,0.14358570118401964,0.5
+8,-1,0.990887513427043,1.0,0.9968673446294058,1.0,0.9998512199273387,1.0,0.14358570118401964,0.5
+9,1304,0.9999655126615866,1.0,0.6497355395474499,0.5,0.6209116788409771,0.5,-0.5194808682062295,-0.5
+9,-1,0.9999655126615866,1.0,0.6497355395474499,0.5,0.6209116788409771,0.5,-0.5194808682062295,-0.5
+10,1304,-0.5719219683411984,-0.5,0.39687881804700254,0.5,0.30235945339824183,0.5,-0.999347111856605,-1.0
+10,-1,-0.5719219683411984,-0.5,0.39687881804700254,0.5,0.30235945339824183,0.5,-0.999347111856605,-1.0
+11,1304,0.9729495464574183,1.0,0.6690539288234543,0.5,0.7507735703666193,0.5,-0.3368830750305066,-0.5
+11,-1,0.9729495464574183,1.0,0.6690539288234543,0.5,0.7507735703666193,0.5,-0.3368830750305066,-0.5
+12,1304,0.03822825127783075,-0.5,0.4190246007667443,0.5,0.28226761527029676,0.5,-0.8074207275431453,-1.0
+12,-1,0.03822825127783075,-0.5,0.4190246007667443,0.5,0.28226761527029676,0.5,-0.8074207275431453,-1.0
+13,1304,-0.12407440060692401,-0.5,0.09294217347959649,-0.5,-0.004266824445988082,-0.5,-0.5787901663098148,-0.5
+13,-1,-0.12407440060692401,-0.5,0.09294217347959649,-0.5,-0.004266824445988082,-0.5,-0.5787901663098148,-0.5
+14,1304,-0.8844436630851609,-1.0,0.15345247129500578,-0.5,0.08044013845351106,-0.5,-0.878190387356299,-0.5
+14,-1,-0.8844436630851609,-1.0,0.15345247129500578,-0.5,0.08044013845351106,-0.5,-0.878190387356299,-0.5
+15,1304,-0.4587053652378529,-0.5,-0.1679422220429646,-0.5,-0.49800060636601906,-0.5,-0.8293174667471915,-1.0
+15,-1,-0.4587053652378529,-0.5,-0.1679422220429646,-0.5,-0.49800060636601906,-0.5,-0.8293174667471915,-1.0
+16,1304,-0.7214189130714723,-1.0,-0.38929415172540693,-0.5,-0.5669329669834173,-0.5,-0.9993262633414052,-1.0
+16,-1,-0.7214189130714723,-1.0,-0.38929415172540693,-0.5,-0.5669329669834173,-0.5,-0.9993262633414052,-1.0
+17,1304,-0.9875055931602853,-1.0,-0.9881595216578223,-1.0,-0.9941001637173952,-1.0,-0.9698495284124343,-1.0
+17,-1,-0.9875055931602853,-1.0,-0.9881595216578223,-1.0,-0.9941001637173952,-1.0,-0.9698495284124343,-1.0
+18,1304,-0.8026210133412679,-1.0,-0.6020057877477804,-0.5,-0.8312749091725715,-1.0,-0.9225987747378575,-1.0
+18,-1,-0.8026210133412679,-1.0,-0.6020057877477804,-0.5,-0.8312749091725715,-1.0,-0.9225987747378575,-1.0
+19,1304,-0.992266321539011,-1.0,-0.9769108517479757,-1.0,-0.9717014178897987,-1.0,-0.999813727966417,-1.0
+19,-1,-0.992266321539011,-1.0,-0.9769108517479757,-1.0,-0.9717014178897987,-1.0,-0.999813727966417,-1.0
+20,1304,-0.9792546213228674,-1.0,-0.9664610069732391,-0.5,-0.9374196416979806,-0.5,-0.9929232049468768,-1.0
+20,-1,-0.9792546213228674,-1.0,-0.9664610069732391,-0.5,-0.9374196416979806,-0.5,-0.9929232049468768,-1.0
+21,1304,-0.8803325781822471,-0.5,-0.8641638472708554,-0.5,-0.8587067700196864,-0.5,-0.8952168921029493,-0.5
+21,-1,-0.8803325781822471,-0.5,-0.8641638472708554,-0.5,-0.8587067700196864,-0.5,-0.8952168921029493,-0.5
+22,1304,-0.9821773066556405,-1.0,-0.967479772085286,-0.5,-0.9395164490452067,-0.5,-0.9978425745891262,-1.0
+22,-1,-0.9821773066556405,-1.0,-0.967479772085286,-0.5,-0.9395164490452067,-0.5,-0.9978425745891262,-1.0
+23,1304,-0.9451937907382904,-0.5,-0.9177608274824107,-0.5,-0.8907700038278844,-0.5,-0.9868671057643829,-1.0
+23,-1,-0.9451937907382904,-0.5,-0.9177608274824107,-0.5,-0.8907700038278844,-0.5,-0.9868671057643829,-1.0
+24,1304,-0.9970052428339253,-1.0,-0.9752457401953942,-1.0,-0.9351725924816069,-0.5,-0.9827461265752002,-1.0
+24,-1,-0.9970052428339253,-1.0,-0.9752457401953942,-1.0,-0.9351725924816069,-0.5,-0.9827461265752002,-1.0
+25,1304,-0.9900665923923802,-1.0,-0.9826019495550782,-1.0,-0.9629348184460832,-0.5,-0.998824896200285,-1.0
+25,-1,-0.9900665923923802,-1.0,-0.9826019495550782,-1.0,-0.9629348184460832,-0.5,-0.998824896200285,-1.0
+26,1304,-0.9708630846146811,-1.0,-0.9630861383788988,-0.5,-0.9402081520993334,-0.5,-0.9838189401770587,-1.0
+26,-1,-0.9708630846146811,-1.0,-0.9630861383788988,-0.5,-0.9402081520993334,-0.5,-0.9838189401770587,-1.0
+27,1304,-0.9656499709168632,-0.5,-0.9512183213026794,-0.5,-0.9376057327109352,-0.5,-0.9881039250604944,-1.0
+27,-1,-0.9656499709168632,-0.5,-0.9512183213026794,-0.5,-0.9376057327109352,-0.5,-0.9881039250604944,-1.0

modules.json

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bc52b1a748af5a4ec351b3e6141b0fc98e6bc51b763476f99288d67322e271c
+size 540060529

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 256,
+  "name_or_path": "neurondbert-finetuned-squad2",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}