Upload folder using huggingface_hub

.ipynb_checkpoints/sentence_bert_config-checkpoint.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 1024,
+  "do_lower_case": false
+}

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 512,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false
+}

README.md

@@ -0,0 +1,130 @@
+---
+library_name: sentence-transformers
+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 512 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 375 with parameters:
+```
+{'batch_size': None, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': '__main__.NoSameLabelsBatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 10,
+    "evaluation_steps": 300,
+    "evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 100,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 1024, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 512, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bge-small-zh-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.3.1",
+    "transformers": "4.37.2",
+    "pytorch": "2.0.1+cu118"
+  }
+}

eval/.ipynb_checkpoints/Information-Retrieval_evaluation_ms-marco-train_eval_results-checkpoint.csv

@@ -0,0 +1,5 @@
+epoch,steps,cos_sim-Accuracy@1,cos_sim-Accuracy@3,cos_sim-Accuracy@5,cos_sim-Accuracy@10,cos_sim-Precision@1,cos_sim-Recall@1,cos_sim-Precision@3,cos_sim-Recall@3,cos_sim-Precision@5,cos_sim-Recall@5,cos_sim-Precision@10,cos_sim-Recall@10,cos_sim-MRR@10,cos_sim-NDCG@10,cos_sim-MAP@100,dot_score-Accuracy@1,dot_score-Accuracy@3,dot_score-Accuracy@5,dot_score-Accuracy@10,dot_score-Precision@1,dot_score-Recall@1,dot_score-Precision@3,dot_score-Recall@3,dot_score-Precision@5,dot_score-Recall@5,dot_score-Precision@10,dot_score-Recall@10,dot_score-MRR@10,dot_score-NDCG@10,dot_score-MAP@100
+0,300,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+0,-1,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+1,300,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+1,-1,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0

eval/Information-Retrieval_evaluation_ms-marco-train_eval_results.csv

@@ -0,0 +1,21 @@
+epoch,steps,cos_sim-Accuracy@1,cos_sim-Accuracy@3,cos_sim-Accuracy@5,cos_sim-Accuracy@10,cos_sim-Precision@1,cos_sim-Recall@1,cos_sim-Precision@3,cos_sim-Recall@3,cos_sim-Precision@5,cos_sim-Recall@5,cos_sim-Precision@10,cos_sim-Recall@10,cos_sim-MRR@10,cos_sim-NDCG@10,cos_sim-MAP@100,dot_score-Accuracy@1,dot_score-Accuracy@3,dot_score-Accuracy@5,dot_score-Accuracy@10,dot_score-Precision@1,dot_score-Recall@1,dot_score-Precision@3,dot_score-Recall@3,dot_score-Precision@5,dot_score-Recall@5,dot_score-Precision@10,dot_score-Recall@10,dot_score-MRR@10,dot_score-NDCG@10,dot_score-MAP@100
+0,300,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+0,-1,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+1,300,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+1,-1,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+2,300,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+2,-1,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+3,300,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+3,-1,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+4,300,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+4,-1,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+5,300,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+5,-1,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+6,300,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+6,-1,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+7,300,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+7,-1,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+8,300,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+8,-1,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+9,300,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0
+9,-1,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.3333333333333333,1.0,0.19999999999999998,1.0,0.09999999999999999,1.0,1.0,1.0,1.0

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a752dc294b6f8d2b14a13f8b93b7c88ccce8d5971cb8448e061208c73761f167
+size 95823472

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": 1024,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}