Update README.md

README.md

@@ -10,135 +10,78 @@ tags:
 widget: []
 ---
 
+Эксперимент по использованию модели, наподобие GPT-2, в качестве эмбеддера. Базовая модель: `ai-forever/rugpt3medium_based_on_gpt2`, извлечено первые 6 слоев.
+
 # SentenceTransformer
 
-This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+Это модель [sentence-transformers](https://www.SBERT.net), которая обучена для преобразования предложений и абзацев в плотное векторное пространство размерностью 1024. Она может использоваться для семантического сопоставления текста, семантического поиска, поиска парафраз, классификации текста, кластеризации и других задач.
 
-## Model Details
+## Описание Модели
 
-### Model Description
-- **Model Type:** Sentence Transformer
-<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
-- **Maximum Sequence Length:** 2048 tokens
-- **Output Dimensionality:** 768 tokens
-- **Similarity Function:** Cosine Similarity
-<!-- - **Training Dataset:** Unknown -->
-<!-- - **Language:** Unknown -->
-<!-- - **License:** Unknown -->
+### Основные Характеристики
+- **Тип модели:** Sentence Transformer
+- **Максимальная длина последовательности:** 2048 токенов
+- **Размерность выхода:** 1024
+- **Функция Similarity:** Косинусное сходство
 
-### Model Sources
+### Источники Модели
 
-- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
-- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
-- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+- **Документация:** [Sentence Transformers Documentation](https://sbert.net)
+- **Репозиторий:** [Sentence Transformers на GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers на Hugging Face](https://huggingface.co/models?library=sentence-transformers)
 
-### Full Model Architecture
+### Полная Архитектура Модели
 
-```
+```python
 SentenceTransformer(
   (0): Transformer({'max_seq_length': 2048, 'do_lower_case': False}) with Transformer model: GPT2Model 
   (1): Pooling({'word_embedding_dimension': 1024, '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})
-  (2): Dense({'in_features': 1024, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.linear.Identity'})
 )
 ```
 
-## Usage
+## Использование
 
-### Direct Usage (Sentence Transformers)
+### Прямое Использование (Sentence Transformers)
 
-First install the Sentence Transformers library:
+Для начала установите библиотеку Sentence Transformers:
 
 ```bash
 pip install -U sentence-transformers
 ```
 
-Then you can load this model and run inference.
+Затем загрузите эту модель и выполните инференс.
+
 ```python
 from sentence_transformers import SentenceTransformer
 
-# Download from the 🤗 Hub
-model = SentenceTransformer("sentence_transformers_model_id")
-# Run inference
+# Загрузка модели с 🤗 Hub
+model = SentenceTransformer("Ponimash/gpt_text_embd")
+# Запуск инференса
 sentences = [
-    'The weather is lovely today.',
-    "It's so sunny outside!",
-    'He drove to the stadium.',
+    'Погода сегодня прекрасная.',
+    'На улице так солнечно!',
+    'Он поехал на стадион.',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
-# [3, 768]
+# [3, 1024]
 
-# Get the similarity scores for the embeddings
+# Получение оценок схожести для эмбеддингов
 similarities = model.similarity(embeddings, embeddings)
 print(similarities.shape)
 # [3, 3]
 ```
 
-<!--
-### Direct Usage (Transformers)
-
-<details><summary>Click to see the direct usage in Transformers</summary>
-
-</details>
--->
-
-<!--
-### Downstream Usage (Sentence Transformers)
-
-You can finetune this model on your own dataset.
-
-<details><summary>Click to expand</summary>
-
-</details>
--->
-
-<!--
-### Out-of-Scope Use
-
-*List how the model may foreseeably be misused and address what users ought not to do with the model.*
--->
-
-<!--
-## Bias, Risks and Limitations
-
-*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
--->
-
-<!--
-### Recommendations
+### Результаты
 
-*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
--->
-
-## Training Details
-
-### Framework Versions
-- Python: 3.10.12
-- Sentence Transformers: 3.0.1
-- Transformers: 4.44.2
-- PyTorch: 2.4.0+cu121
-- Accelerate: 0.33.0
-- Datasets: 2.21.0
-- Tokenizers: 0.19.1
-
-## Citation
-
-### BibTeX
-
-<!--
-## Glossary
-
-*Clearly define terms in order to be accessible across audiences.*
--->
-
-<!--
-## Model Card Authors
-
-*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
--->
-
-<!--
-## Model Card Contact
+```python
+# Выходная размерность: 1024
+tensor([[1.0000, 0.6575, 0.4605],
+        [0.6575, 1.0000, 0.4683],
+        [0.4605, 0.4683, 1.0000]])
 
-*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--->
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 2048, 'do_lower_case': False}) with Transformer model: GPT2Model 
+  (1): Pooling({'word_embedding_dimension': 1024, '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})
+)
+```