Upload 14 files

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "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,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,180 @@
+---
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+  - sentence-transformers
+  - feature-extraction
+  - sentence-similarity
+  - transformers
+---
+
+# Enbeddrus v0.1 D+PC - English and Russian embedder
+
+> This is the model trained on Domain, then Parallel Corpora
+
+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.
+
+- **Parameters**: 168 million
+- **Layers**: 12
+- **Hidden Size**: 768
+- **Attention Heads**: 12
+- **Vocabulary Size**: 119,547
+- **Maximum Sequence Length**: 512 tokens
+
+The Enbeddrus model is designed to extract similar embeddings for comparable English and Russian phrases. It is based on
+the [bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-cased) model and was
+trained over 20 epochs on the following datasets:
+
+- [evilfreelancer/opus-php-en-ru-cleaned](https://huggingface.co/datasets/evilfreelancer/opus-php-en-ru-cleaned) (
+  train): 1.6k lines
+- [Helsinki-NLP/opus_books](https://huggingface.co/datasets/Helsinki-NLP/opus_books/viewer/en-ru) (en-ru, train): 17.5k
+  lines
+
+The goal of this model is to generate identical or very similar embeddings regardless of whether the text is written in
+English or Russian.
+
+## 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 = [
+    "PHP является скриптовым языком программирования, широко используемым для веб-разработки.",
+    "PHP is a scripting language widely used for web development.",
+    "PHP поддерживает множество баз данных, таких как MySQL, PostgreSQL и SQLite.",
+    "PHP supports many databases like MySQL, PostgreSQL, and SQLite.",
+    "Функция echo в PHP используется для вывода текста на экран.",
+    "The echo function in PHP is used to output text to the screen.",
+    "Машинное обучение помогает создавать интеллектуальные системы.",
+    "Machine learning helps to create intelligent systems.",
+]
+
+model = SentenceTransformer('evilfreelancer/enbeddrus')
+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 = [
+    "PHP является скриптовым языком программирования, широко используемым для веб-разработки.",
+    "PHP is a scripting language widely used for web development.",
+    "PHP поддерживает множество баз данных, таких как MySQL, PostgreSQL и SQLite.",
+    "PHP supports many databases like MySQL, PostgreSQL, and SQLite.",
+    "Функция echo в PHP используется для вывода текста на экран.",
+    "The echo function in PHP is used to output text to the screen.",
+    "Машинное обучение помогает создавать интеллектуальные системы.",
+    "Machine learning helps to create intelligent systems.",
+]
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('evilfreelancer/enbeddrus')
+model = AutoModel.from_pretrained('evilfreelancer/enbeddrus')
+
+# 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
+
+The model was tested on the `eval` split of the
+dataset [evilfreelancer/opus-php-en-ru-cleaned](https://huggingface.co/datasets/evilfreelancer/opus-php-en-ru-cleaned),
+which contains 100 pairs of sentences in Russian and English on the topic of PHP. The results of the testing are
+presented in the image below.
+
+![Evaluation Results](./eval.png)
+
+* **Left**: Embedding similarity in Russian and English before training
+  (the points are spread out into two distinct clusters).
+* **Center**: Embedding similarity after training
+  (the points representing similar phrases are very close to each other).
+* **Right**: Cosine distance before and after training.
+
+## Training
+
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 556 with parameters:
+
+```python
+{
+    'batch_size': 64,
+    'sampler': 'torch.utils.data.sampler.RandomSampler',
+    'batch_sampler': 'torch.utils.data.sampler.BatchSampler'
+}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MSELoss.MSELoss`
+
+Parameters of the fit()-Method:
+
+```
+{
+    "epochs": 20,
+    "evaluation_steps": 100,
+    "evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "eps": 1e-06,
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 10000,
+    "weight_decay": 0.01
+}
+```
+
+## Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (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, 'include_prompt': True})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bert-base-multilingual-uncased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105879
+}

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.7.0",
+    "transformers": "4.40.2",
+    "pytorch": "2.3.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

eval/mse_evaluation_talks-en-ru-dev.tsv.gz_results.csv

@@ -0,0 +1,29 @@
+epoch,steps,MSE
+0,100,2.878684550523758
+0,200,2.5711659342050552
+0,300,2.2758182138204575
+0,400,2.1430378779768944
+0,500,2.025136351585388
+0,-1,1.9794309511780739
+1,100,1.8464291468262672
+1,200,1.7591631039977074
+1,300,1.699366606771946
+1,400,1.635102741420269
+1,500,1.5872221440076828
+1,-1,1.576891914010048
+2,100,1.5398328192532063
+2,200,1.5269143506884575
+2,300,1.4953669160604477
+2,400,1.468233484774828
+2,500,1.4520802535116673
+2,-1,1.4370085671544075
+3,100,1.4182819053530693
+3,200,1.4062595553696156
+3,300,1.4026491902768612
+3,400,1.3922274112701416
+3,500,1.3593204319477081
+3,-1,1.3746432028710842
+4,100,1.3601386919617653
+4,200,1.346716657280922
+4,300,1.3340381905436516
+4,400,1.3312975876033306

eval/translation_evaluation_talks-en-ru-dev.tsv.gz_results.csv

@@ -0,0 +1,29 @@
+epoch,steps,src2trg,trg2src
+0,100,0.718,0.681
+0,200,0.727,0.69
+0,300,0.747,0.713
+0,400,0.755,0.729
+0,500,0.759,0.743
+0,-1,0.762,0.745
+1,100,0.769,0.759
+1,200,0.77,0.765
+1,300,0.777,0.771
+1,400,0.784,0.778
+1,500,0.79,0.778
+1,-1,0.792,0.779
+2,100,0.793,0.783
+2,200,0.798,0.782
+2,300,0.797,0.783
+2,400,0.808,0.792
+2,500,0.812,0.791
+2,-1,0.811,0.791
+3,100,0.816,0.795
+3,200,0.816,0.797
+3,300,0.819,0.797
+3,400,0.832,0.799
+3,500,0.835,0.801
+3,-1,0.834,0.797
+4,100,0.839,0.803
+4,200,0.844,0.809
+4,300,0.844,0.809
+4,400,0.845,0.807

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e331bc4bcae366b4070862cc6fc98a8b91d2d3b91cdb9efa3d096fb03725a0
+size 669448040

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 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}