Upload with huggingface_hub

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-  "word_embedding_dimension": 768,
+  "word_embedding_dimension": 384,
   "pooling_mode_cls_token": false,
   "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,

README.md

@@ -4,13 +4,12 @@ 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.
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
 <!--- Describe your model here -->
 
@@ -35,44 +34,6 @@ 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 -->
@@ -85,7 +46,7 @@ The model was trained with the parameters:
 
 **DataLoader**:
 
-`torch.utils.data.dataloader.DataLoader` of length 1 with parameters:
+`torch.utils.data.dataloader.DataLoader` of length 1369 with parameters:
 ```
 {'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
@@ -110,7 +71,7 @@ Parameters of the fit()-Method:
     },
     "scheduler": "WarmupLinear",
     "steps_per_epoch": null,
-    "warmup_steps": 1,
+    "warmup_steps": 1369,
     "weight_decay": 0.01
 }
 ```
@@ -119,8 +80,9 @@ Parameters of the fit()-Method:
 ## Full Model Architecture
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel 
-  (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})
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+  (2): Normalize()
 )
 ```
 

config.json

@@ -1,24 +1,26 @@
 {
-  "_name_or_path": "/home/jtang/.cache/torch/sentence_transformers/sentence-transformers_msmarco-distilbert-dot-v5/",
-  "activation": "gelu",
+  "_name_or_path": "/home/jtang/.cache/torch/sentence_transformers/sentence-transformers_multi-qa-MiniLM-L6-cos-v1/",
   "architectures": [
-    "DistilBertModel"
+    "BertModel"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
   "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.26.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

modules.json

@@ -10,5 +10,11 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
   }
 ]

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea71ca5fdecde873030ba6d8c648c4c0bbf25de7880b35fd09c3f11b34fbe25e
-size 265484701
+oid sha256:ea83c0bc402863aaaea0d8cf6002f1da792a5c625eb7441d9295ceb5eed1d30e
+size 90891565

tokenizer_config.json

@@ -1,14 +1,16 @@
 {
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "/home/jtang/.cache/torch/sentence_transformers/sentence-transformers_msmarco-distilbert-dot-v5/",
+  "name_or_path": "/home/jtang/.cache/torch/sentence_transformers/sentence-transformers_multi-qa-MiniLM-L6-cos-v1/",
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }