add sentence

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
+}

2_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 768, "bias": false, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c2d8106dd315cd2a0b39459de220455a21d289b1f4cb1eb9c364dde3570c9c6
+size 1179736

README.md

@@ -0,0 +1,123 @@
+---
+language:
+- en
+- ru
+- zh
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- text2text-generation
+- t5
+base_model:
+  - utrobinmv/t5_translate_en_ru_zh_base_200
+license: apache-2.0
+widget:
+  - example_title: translate zh-ru
+    text: >
+      translate to ru: 开发的目的是为用户提供个人同步翻译。
+  - example_title: translate ru-en
+    text: >
+      translate to en: Цель разработки — предоставить пользователям личного синхронного переводчика.
+  - example_title: translate en-ru
+    text: >
+      translate to ru: The purpose of the development is to provide users with a personal synchronized interpreter.
+  - example_title: translate en-zh
+    text: >
+      translate to zh: The purpose of the development is to provide users with a personal synchronized interpreter.
+  - example_title: translate zh-en
+    text: >
+      translate to en: 开发的目的是为用户提供个人同步解释器。
+  - example_title: translate ru-zh
+    text: >
+      translate to zh: Цель разработки — предоставить пользователям личного синхронного переводчика.
+---
+
+# T5 English, Russian and Chinese multilingual machine translation
+
+This is a [sentence-transformers](https://www.sbert.net/) model: It maps sentences & paragraphs to a 768 dimensional dense vector space. The model works well for sentence similarity tasks, but doesn't perform that well for semantic search tasks.
+
+The model uses only the encoder from a T5-base model.
+
+
+## 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('sentence-transformers/sentence-t5-base')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+Example translate Russian to Chinese
+
+```python
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+
+device = 'cuda' #or 'cpu' for translate on cpu
+
+model_name = 'utrobinmv/t5_translate_en_ru_zh_large_1024'
+model = T5ForConditionalGeneration.from_pretrained(model_name)
+model.to(device)
+tokenizer = T5Tokenizer.from_pretrained(model_name)
+
+prefix = 'translate to zh: '
+src_text = prefix + "Съешь ещё этих мягких французских булок."
+
+# translate Russian to Chinese
+input_ids = tokenizer(src_text, return_tensors="pt")
+
+generated_tokens = model.generate(**input_ids.to(device))
+
+result = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
+print(result)
+# 再吃这些法国的甜蜜的面包。
+```
+
+
+
+and Example translate Chinese to Russian
+
+```python
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+
+device = 'cuda' #or 'cpu' for translate on cpu
+
+model_name = 'utrobinmv/t5_translate_en_ru_zh_large_1024'
+model = T5ForConditionalGeneration.from_pretrained(model_name)
+model.to(device)
+tokenizer = T5Tokenizer.from_pretrained(model_name)
+
+prefix = 'translate to ru: '
+src_text = prefix + "再吃这些法国的甜蜜的面包。"
+
+# translate Russian to Chinese
+input_ids = tokenizer(src_text, return_tensors="pt")
+
+generated_tokens = model.generate(**input_ids.to(device))
+
+result = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
+print(result)
+# Съешьте этот сладкий хлеб из Франции.
+```
+
+
+
+##  
+
+
+
+## Languages covered
+
+Russian (ru_RU), Chinese (zh_CN), English (en_US)

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.38.2",
+    "pytorch": "2.2.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cos_sim"
+}

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "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})",
+    "path": "1_Pooling",
+    "type": "models.Pooling"
+  },
+  {
+    "idx": 1,
+    "name": "Dense({'in_features': 768, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.activation.Tanh'})",
+    "path": "2_Dense",
+    "type": "models.Dense"
+  },
+  {
+    "idx": 2,
+    "name": "Normalize()",
+    "path": "3_Normalize",
+    "type": "models.Normalize"
+  }
+]