Upload 11 files

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 +1,94 @@
+---
+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})
+
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel 
+  (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 +1,107 @@
+{
+  "X509": 30611,
+  "aad": 30627,
+  "acl": 30559,
+  "acm": 30597,
+  "alpn": 30601,
+  "arn": 30591,
+  "asr": 30532,
+  "auc": 30562,
+  "auth": 30593,
+  "aws": 30547,
+  "bgp": 30622,
+  "cdk": 30545,
+  "cdn": 30542,
+  "chime": 30535,
+  "cidr": 30617,
+  "cidr ": 30603,
+  "cli": 30595,
+  "cloud9": 30539,
+  "cloudfront": 30620,
+  "cloudhsm": 30625,
+  "cloudquery": 30587,
+  "cloudtrail": 30546,
+  "cloudwatch": 30629,
+  "cmk": 30602,
+  "cognito": 30612,
+  "config": 30596,
+  "csv": 30581,
+  "devops": 30580,
+  "dhcp": 30623,
+  "dms": 30607,
+  "dns": 30530,
+  "docker": 30579,
+  "ebs": 30569,
+  "ec2": 30527,
+  "ecr": 30557,
+  "ecs": 30550,
+  "efs": 30564,
+  "eks": 30592,
+  "elb": 30574,
+  "emr": 30537,
+  "etl": 30567,
+  "git": 30570,
+  "github": 30621,
+  "gpu": 30568,
+  "gw": 30614,
+  "hdfs": 30552,
+  "hmac": 30558,
+  "hpc": 30531,
+  "hrnn": 30630,
+  "hsm": 30615,
+  "hvm": 30624,
+  "iam": 30541,
+  "iops": 30582,
+  "ipsec": 30565,
+  "ipv4": 30590,
+  "ipv6": 30589,
+  "isp": 30560,
+  "isps": 30563,
+  "itsm": 30585,
+  "kinesis": 30609,
+  "kms": 30584,
+  "kubernetes": 30594,
+  "mime": 30631,
+  "mysql": 30572,
+  "namespace": 30613,
+  "nif": 30604,
+  "nosql": 30577,
+  "oai": 30534,
+  "rds": 30544,
+  "redis": 30533,
+  "redshift": 30529,
+  "route53": 30619,
+  "s3": 30538,
+  "saas": 30551,
+  "saml": 30555,
+  "scp": 30543,
+  "sct": 30540,
+  "sdk": 30536,
+  "snapshot": 30606,
+  "sns": 30586,
+  "spf": 30578,
+  "sqs": 30571,
+  "sse": 30626,
+  "ssh": 30528,
+  "ssl": 30583,
+  "ssm": 30588,
+  "subnet": 30566,
+  "swf": 30561,
+  "tcp": 30610,
+  "tgw": 30616,
+  "throttling": 30554,
+  "tls": 30573,
+  "upt": 30600,
+  "uptycs": 30618,
+  "url": 30605,
+  "vgw": 30576,
+  "vm": 30575,
+  "vms": 30549,
+  "vmware": 30548,
+  "vpc": 30556,
+  "vpn": 30553,
+  "waf": 30598,
+  "wam": 30628,
+  "webacl": 30608,
+  "wsdl": 30599
+}

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "/home/pmane/.cache/torch/sentence_transformers/sentence-transformers_multi-qa-mpnet-base-dot-v1/",
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "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": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "vocab_size": 30632
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.29.2",
+    "pytorch": "2.0.1+cpu"
+  }
+}

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"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "unk_token": "[UNK]"
+}