Upload 17 files

README.md

@@ -0,0 +1,168 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+library_name: generic
+language:
+- vi
+widget:
+- source_sentence: Làm thế nào Đại học Bách khoa Hà Nội thu hút sinh viên quốc tế?
+  sentences:
+  - >-
+    Đại học Bách khoa Hà Nội đã phát triển các chương trình đào tạo bằng tiếng
+    Anh để làm cho việc học tại đây dễ dàng hơn cho sinh viên quốc tế.
+  - >-
+    Môi trường học tập đa dạng và sự hỗ trợ đầy đủ cho sinh viên quốc tế tại Đại
+    học Bách khoa Hà Nội giúp họ thích nghi nhanh chóng.
+  - Hà Nội có khí hậu mát mẻ vào mùa thu.
+  - Các món ăn ở Hà Nội rất ngon và đa dạng.
+license: apache-2.0
+---
+
+# bkai-foundation-models/vietnamese-bi-encoder
+
+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.
+
+We train the model on a merged training dataset that consists of: 
+  - MS Macro (translated into Vietnamese)
+  - SQuAD v2  (translated into Vietnamese)
+  - 80% of the training set from the Legal Text Retrieval Zalo 2021 challenge
+
+We use [phobert-base-v2](https://github.com/VinAIResearch/PhoBERT) as the pre-trained backbone.
+
+Here are the results on the remaining 20% of the training set from the Legal Text Retrieval Zalo 2021 challenge:
+
+|     Pretrained Model          |     Training Datasets                  |     Acc@1    |     Acc@10    |     Acc@100    |     Pre@10    |     MRR@10    |
+|-------------------------------|---------------------------------------|:------------:|:-------------:|:--------------:|:-------------:|:-------------:|
+|     [Vietnamese-SBERT](https://huggingface.co/keepitreal/vietnamese-sbert)     |     -                                 |     32.34    |      52.97    |      89.84     |      7.05     |      45.30    |
+|     PhoBERT-base-v2           |     MSMACRO                           |     47.81    |      77.19    |      92.34     |      7.72     |      58.37    |
+|     PhoBERT-base-v2                            |     MSMACRO + SQuADv2.0 + 80% Zalo    |     73.28    |      93.59    |      98.85     |      9.36     |      80.73    |
+
+
+<!--- 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
+
+# INPUT TEXT MUST BE ALREADY WORD-SEGMENTED!
+sentences = ["Cô ấy là một người vui_tính .", "Cô ấy cười nói suốt cả ngày ."]
+
+model = SentenceTransformer('bkai-foundation-models/vietnamese-bi-encoder')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+## Usage (Widget HuggingFace)
+The widget use custom pipeline on top of the default pipeline by adding additional word segmenter before PhobertTokenizer. So you do not need to segment words before using the API:
+
+An example could be seen in Hosted inference API.
+ 
+
+## 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, we could use pyvi, underthesea, RDRSegment to segment words
+sentences = ['Cô ấy là một người vui_tính .', 'Cô ấy cười nói suốt cả ngày .']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('bkai-foundation-models/vietnamese-bi-encoder')
+model = AutoModel.from_pretrained('bkai-foundation-models/vietnamese-bi-encoder')
+
+# 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)
+```
+
+## Training
+
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 17584 with parameters:
+
+```
+{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', '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": 15,
+    "evaluation_steps": 0,
+    "evaluator": "NoneType",
+    "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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
+)
+```
+
+### Please cite our manuscript if this dataset is used for your work
+```
+  @article{duc2024towards,
+    title={Towards Comprehensive Vietnamese Retrieval-Augmented Generation and Large Language Models},
+    author={Nguyen Quang Duc, Le Hai Son, Nguyen Duc Nhan, Nguyen Dich Nhat Minh, Le Thanh Huong, Dinh Viet Sang},
+    journal={arXiv preprint arXiv:2403.01616},
+    year={2024}
+  }
+```

added_tokens.json

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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "bkai-foundation-models/vietnamese-bi-encoder",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "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": 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": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.32.0",
+    "pytorch": "2.0.0+cu117"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b54fa517ddb1b719a3a3503553941b7ac3f5e461710f5409e596d1af9fe567
+size 540015464

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"
+  }
+]

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8fc64d9afbb9f3b6cc460bb0ae7edbe3d4d95beeef191e310675ff2df1450f
+size 1075428986

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecd28a54b12bde3537c1ae118d1c686cba3ea30605cf89bfdac2f1c889d3b513
+size 14512

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698dd5ce82f28d4ada87e4512bb18826853b15318abbd51003665abb635e7dab
+size 14512

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f60d1d2d190161d57aafae98632eb27f6d5335b31b913c32c549cfeb405fc0a
+size 1064

sentence_bert_config.json

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

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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": "</s>",
+    "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 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,246 @@
+{
+  "best_metric": 0.7469254634972615,
+  "best_model_checkpoint": "checkpoints/bkai-foundation-models-vietnamese-bi-encoder-sts_example-Apr-11_09-40/checkpoint-9",
+  "epoch": 0.9230769230769231,
+  "eval_steps": 1,
+  "global_step": 9,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.4329559803009033,
+      "learning_rate": 2e-05,
+      "loss": 0.2895,
+      "step": 1
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.17446795105934143,
+      "eval_pearson_cosine": 0.7352753127420032,
+      "eval_pearson_dot": 0.686758677756194,
+      "eval_pearson_euclidean": 0.7173498836125568,
+      "eval_pearson_manhattan": 0.7148706172408587,
+      "eval_pearson_max": 0.7352753127420032,
+      "eval_runtime": 4.9797,
+      "eval_samples_per_second": 20.082,
+      "eval_spearman_cosine": 0.7210935594862063,
+      "eval_spearman_dot": 0.6923873928081955,
+      "eval_spearman_euclidean": 0.7268846214769229,
+      "eval_spearman_manhattan": 0.7230502456992293,
+      "eval_spearman_max": 0.7268846214769229,
+      "eval_steps_per_second": 0.201,
+      "step": 1
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.5664677619934082,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.3072,
+      "step": 2
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.14536823332309723,
+      "eval_pearson_cosine": 0.7443285684058452,
+      "eval_pearson_dot": 0.7004870662431258,
+      "eval_pearson_euclidean": 0.7311397302983574,
+      "eval_pearson_manhattan": 0.7298089636403461,
+      "eval_pearson_max": 0.7443285684058452,
+      "eval_runtime": 4.9136,
+      "eval_samples_per_second": 20.352,
+      "eval_spearman_cosine": 0.7313692004372047,
+      "eval_spearman_dot": 0.6972061883576584,
+      "eval_spearman_euclidean": 0.7333137333197118,
+      "eval_spearman_manhattan": 0.7343163830872546,
+      "eval_spearman_max": 0.7343163830872546,
+      "eval_steps_per_second": 0.204,
+      "step": 2
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.1925618648529053,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.2494,
+      "step": 3
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.13241076469421387,
+      "eval_pearson_cosine": 0.7475582818227843,
+      "eval_pearson_dot": 0.7072187737528184,
+      "eval_pearson_euclidean": 0.7395368453244974,
+      "eval_pearson_manhattan": 0.7390320701180779,
+      "eval_pearson_max": 0.7475582818227843,
+      "eval_runtime": 4.9299,
+      "eval_samples_per_second": 20.284,
+      "eval_spearman_cosine": 0.734443993057669,
+      "eval_spearman_dot": 0.7085877823855826,
+      "eval_spearman_euclidean": 0.7370326524575067,
+      "eval_spearman_manhattan": 0.7358051660754241,
+      "eval_spearman_max": 0.7370326524575067,
+      "eval_steps_per_second": 0.203,
+      "step": 3
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.7575017809867859,
+      "learning_rate": 1.25e-05,
+      "loss": 0.2055,
+      "step": 4
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.12977080047130585,
+      "eval_pearson_cosine": 0.7480467529027109,
+      "eval_pearson_dot": 0.7098231030406952,
+      "eval_pearson_euclidean": 0.744921218850896,
+      "eval_pearson_manhattan": 0.7451527031212235,
+      "eval_pearson_max": 0.7480467529027109,
+      "eval_runtime": 4.8972,
+      "eval_samples_per_second": 20.42,
+      "eval_spearman_cosine": 0.7384545921278399,
+      "eval_spearman_dot": 0.7140993177744387,
+      "eval_spearman_euclidean": 0.7418271413459383,
+      "eval_spearman_manhattan": 0.7415597680745935,
+      "eval_spearman_max": 0.7418271413459383,
+      "eval_steps_per_second": 0.204,
+      "step": 4
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.5988340973854065,
+      "learning_rate": 1e-05,
+      "loss": 0.1953,
+      "step": 5
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.13172687590122223,
+      "eval_pearson_cosine": 0.7481749312063645,
+      "eval_pearson_dot": 0.7114101061443809,
+      "eval_pearson_euclidean": 0.7487853408979873,
+      "eval_pearson_manhattan": 0.7493155754097085,
+      "eval_pearson_max": 0.7493155754097085,
+      "eval_runtime": 4.9354,
+      "eval_samples_per_second": 20.262,
+      "eval_spearman_cosine": 0.7410797115192246,
+      "eval_spearman_dot": 0.715740017394054,
+      "eval_spearman_euclidean": 0.7440876608218527,
+      "eval_spearman_manhattan": 0.7416873780450081,
+      "eval_spearman_max": 0.7440876608218527,
+      "eval_steps_per_second": 0.203,
+      "step": 5
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.45404252409935,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.1955,
+      "step": 6
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.13533657789230347,
+      "eval_pearson_cosine": 0.7481572181840599,
+      "eval_pearson_dot": 0.7119585324914705,
+      "eval_pearson_euclidean": 0.7513750385090986,
+      "eval_pearson_manhattan": 0.7520214602427692,
+      "eval_pearson_max": 0.7520214602427692,
+      "eval_runtime": 4.9045,
+      "eval_samples_per_second": 20.389,
+      "eval_spearman_cosine": 0.7413227781295381,
+      "eval_spearman_dot": 0.7178243135774913,
+      "eval_spearman_euclidean": 0.7454609871701232,
+      "eval_spearman_manhattan": 0.7439235908598911,
+      "eval_spearman_max": 0.7454609871701232,
+      "eval_steps_per_second": 0.204,
+      "step": 6
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.29167646169662476,
+      "learning_rate": 5e-06,
+      "loss": 0.1817,
+      "step": 7
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.1384459137916565,
+      "eval_pearson_cosine": 0.7486794628287365,
+      "eval_pearson_dot": 0.7128799880836781,
+      "eval_pearson_euclidean": 0.7534668223526225,
+      "eval_pearson_manhattan": 0.7542705307695821,
+      "eval_pearson_max": 0.7542705307695821,
+      "eval_runtime": 4.8885,
+      "eval_samples_per_second": 20.456,
+      "eval_spearman_cosine": 0.7447864773265037,
+      "eval_spearman_dot": 0.7191307966079258,
+      "eval_spearman_euclidean": 0.7470348434719025,
+      "eval_spearman_manhattan": 0.7471259934507699,
+      "eval_spearman_max": 0.7471259934507699,
+      "eval_steps_per_second": 0.205,
+      "step": 7
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.2743995785713196,
+      "learning_rate": 2.5e-06,
+      "loss": 0.1779,
+      "step": 8
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 0.14035974442958832,
+      "eval_pearson_cosine": 0.7493716294557077,
+      "eval_pearson_dot": 0.7139035538213145,
+      "eval_pearson_euclidean": 0.7549035222973965,
+      "eval_pearson_manhattan": 0.755825827892859,
+      "eval_pearson_max": 0.755825827892859,
+      "eval_runtime": 4.9234,
+      "eval_samples_per_second": 20.311,
+      "eval_spearman_cosine": 0.7468890035057144,
+      "eval_spearman_dot": 0.7218835259697248,
+      "eval_spearman_euclidean": 0.7492406729604966,
+      "eval_spearman_manhattan": 0.7483170198413056,
+      "eval_spearman_max": 0.7492406729604966,
+      "eval_steps_per_second": 0.203,
+      "step": 8
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.2744670808315277,
+      "learning_rate": 0.0,
+      "loss": 0.1778,
+      "step": 9
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 0.14107824862003326,
+      "eval_pearson_cosine": 0.7498873452997028,
+      "eval_pearson_dot": 0.7146359714365732,
+      "eval_pearson_euclidean": 0.7556639064226516,
+      "eval_pearson_manhattan": 0.7566449947956903,
+      "eval_pearson_max": 0.7566449947956903,
+      "eval_runtime": 4.89,
+      "eval_samples_per_second": 20.45,
+      "eval_spearman_cosine": 0.7469254634972615,
+      "eval_spearman_dot": 0.7228071790889158,
+      "eval_spearman_euclidean": 0.7491738296426602,
+      "eval_spearman_manhattan": 0.7486816197567756,
+      "eval_spearman_max": 0.7491738296426602,
+      "eval_steps_per_second": 0.205,
+      "step": 9
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 9,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1,
+  "total_flos": 0.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668b6b369a532d848cfe9611573fbe1fe3274136bc4c59d99fb8e9e3c1a4388b
+size 5176