Update README.md
Browse files
README.md
CHANGED
@@ -15,11 +15,11 @@ datasets:
|
|
15 |
|
16 |
#### RU
|
17 |
|
18 |
-
Инструктивная модель на основе **Qwen-2.5-1.5B-Instruct**, обученная на русскоязычном датасете **GrandMaster-PRO-MAX**.
|
19 |
|
20 |
#### EN
|
21 |
|
22 |
-
Instructive model based on **Qwen-2.5-1.5B-Instruct**, trained on the Russian-language dataset **GrandMaster-PRO-MAX**.
|
23 |
|
24 |
## GGUF
|
25 |
|
@@ -91,3 +91,26 @@ output = model.generate(
|
|
91 |
# Decode and print result
|
92 |
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
|
93 |
print(generated_text)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
|
16 |
#### RU
|
17 |
|
18 |
+
Инструктивная модель на основе **Qwen-2.5-1.5B-Instruct**, обученная на русскоязычном датасете **GrandMaster-PRO-MAX**. Создана для высокоэффективной обработки текстов на русском и английском языках, обеспечивая точные ответы и быстрое выполнение задач.
|
19 |
|
20 |
#### EN
|
21 |
|
22 |
+
Instructive model based on **Qwen-2.5-1.5B-Instruct**, trained on the Russian-language dataset **GrandMaster-PRO-MAX**. Designed for high-efficiency text processing in Russian and English, delivering precise responses and fast task execution.
|
23 |
|
24 |
## GGUF
|
25 |
|
|
|
91 |
# Decode and print result
|
92 |
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
|
93 |
print(generated_text)
|
94 |
+
```
|
95 |
+
|
96 |
+
#### Ответ модели / Model response:
|
97 |
+
|
98 |
+
>Книга "Гарри Поттер" — это популярное произведение в жанре фэнтези, которое исследует темы дружбы, магии и борьбы со злом. Главный герой проходит путь взросления, преодолевая препятствия и сталкиваясь с моральными вызовами.
|
99 |
+
|
100 |
+
### Авторы / Authors
|
101 |
+
|
102 |
+
- Sergei Bratchikov, [NLP Wanderer](https://t.me/nlpwanderer), [Vikhr Team](https://t.me/vikhrlabs)
|
103 |
+
- Nikolay Kompanets, [LakoMoor](https://t.me/lakomoordev), [Vikhr Team](https://t.me/vikhrlabs)
|
104 |
+
- Konstantin Korolev, [Vikhr Team](https://t.me/vikhrlabs)
|
105 |
+
- Aleksandr Nikolich, [Vikhr Team](https://t.me/vikhrlabs)
|
106 |
+
|
107 |
+
```
|
108 |
+
@inproceedings{nikolich2024vikhr,
|
109 |
+
title={Vikhr: Advancing Open-Source Bilingual Instruction-Following Large Language Models for Russian and English},
|
110 |
+
author={Aleksandr Nikolich and Konstantin Korolev and Sergei Bratchikov and Nikolay Kompanets and Igor Kiselev and Artem Shelmanov},
|
111 |
+
booktitle={Proceedings of the 4th Workshop on Multilingual Representation Learning (MRL) @ EMNLP-2024},
|
112 |
+
year={2024},
|
113 |
+
publisher={Association for Computational Linguistics},
|
114 |
+
url={https://arxiv.org/pdf/2405.13929}
|
115 |
+
}
|
116 |
+
```
|