Upload 13 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 +1,129 @@
+---
+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 28 with parameters:
+```
+{'batch_size': 32, 'sampler': 'torch.utils.data.dataloader._InfiniteConstantSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 4,
+    "evaluation_steps": 5000,
+    "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": 1000,
+    "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": "/root/.cache/torch/sentence_transformers/khanhbk20_vn-sentence-embedding/",
+  "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": "4.31.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.0",
+    "transformers": "4.11.3",
+    "pytorch": "1.10.2+cpu"
+  }
+}

eval/Information-Retrieval_evaluation_results.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,-1,0.25892857142857145,0.35714285714285715,0.49107142857142855,0.6964285714285714,0.25892857142857145,0.25892857142857145,0.11904761904761904,0.35714285714285715,0.09821428571428571,0.49107142857142855,0.06964285714285713,0.6964285714285714,0.3577628968253969,0.43585964350872264,0.37390056352190054,0.25892857142857145,0.4017857142857143,0.4732142857142857,0.6964285714285714,0.25892857142857145,0.25892857142857145,0.13392857142857142,0.4017857142857143,0.09464285714285713,0.4732142857142857,0.06964285714285713,0.6964285714285714,0.3641794217687075,0.4409194658852294,0.3803820909646762
+1,-1,0.25892857142857145,0.35714285714285715,0.49107142857142855,0.6964285714285714,0.25892857142857145,0.25892857142857145,0.11904761904761904,0.35714285714285715,0.09821428571428571,0.49107142857142855,0.06964285714285713,0.6964285714285714,0.3604308390022677,0.43804296984390484,0.3765754123075687,0.25892857142857145,0.4107142857142857,0.4732142857142857,0.6875,0.25892857142857145,0.25892857142857145,0.13690476190476192,0.4107142857142857,0.09464285714285713,0.4732142857142857,0.06874999999999999,0.6875,0.36418296485260765,0.4391090121547106,0.3811592600531137
+2,-1,0.25892857142857145,0.36607142857142855,0.48214285714285715,0.6964285714285714,0.25892857142857145,0.25892857142857145,0.12202380952380952,0.36607142857142855,0.09642857142857142,0.48214285714285715,0.06964285714285713,0.6964285714285714,0.3606434240362812,0.4382012548861899,0.3766254192890954,0.25892857142857145,0.4107142857142857,0.49107142857142855,0.7053571428571429,0.25892857142857145,0.25892857142857145,0.13690476190476192,0.4107142857142857,0.09821428571428571,0.49107142857142855,0.07053571428571427,0.7053571428571429,0.3668473639455783,0.4450492819181417,0.38219516880910614
+3,-1,0.25892857142857145,0.36607142857142855,0.48214285714285715,0.6964285714285714,0.25892857142857145,0.25892857142857145,0.12202380952380952,0.36607142857142855,0.09642857142857142,0.48214285714285715,0.06964285714285713,0.6964285714285714,0.36044855442176876,0.4379881801985434,0.37627618787551054,0.26785714285714285,0.4107142857142857,0.5,0.6785714285714286,0.26785714285714285,0.26785714285714285,0.1369047619047619,0.4107142857142857,0.09999999999999999,0.5,0.06785714285714285,0.6785714285714286,0.3667835884353741,0.4391108357522167,0.38457454902855986

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:cedb6f80d40de147265a7a3292a5853ddf53f38d10c6c3e395f4a371533042a8
+size 540059817

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>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>"
+}