Total runs:
51.7K
Run Growth:
-3.0K
Growth Rate:
-5.71%
Sponsored by
Vmake Labs Video Enhancer
Vikhrmodels / Vikhr-Qwen-2.5-1.5B-Instruct
Model's Last Updated: November 27 2024
text-generation
Introduction of Vikhr-Qwen-2.5-1.5B-Instruct
Model Details of Vikhr-Qwen-2.5-1.5B-Instruct
💨🦅 Vikhr-Qwen-2.5-1.5B-Instruct
RU
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.
EN
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.
Quatized variants:
Особенности:
- 📚 Основа / Base: Qwen-2.5-1.5B-Instruct
- 🇷🇺 Специализация / Specialization: RU
- 💾 Датасет / Dataset: GrandMaster-PRO-MAX
- 🌍 Поддержка: Bilingual RU/EN
Попробовать / Try now:
Описание:
RU
Vikhr-Qwen-2.5-1.5B-Instruct — мощная языковая модель, обученная на датасете GrandMaster-PRO-MAX , поддерживает генерацию инструкций, контекстные ответы и анализ текста на русском языке. Эта модель оптимизирована для задач инструктивного обучения и обработки текстов. Она подходит для использования в профессиональной среде, а также для интеграции в пользовательские приложения и сервисы.
EN
Vikhr-Qwen-2.5-1.5B-Instruct is a robust language model trained on the GrandMaster-PRO-MAX dataset. It excels in instruction generation, contextual responses, and text analysis in Russian. The model is optimized for instructional tasks and textual data processing, suitable for professional use as well as integration into user-facing applications and services.
Обучение / Training:
RU
Vikhr-Qwen-2.5-1.5B-Instruct была создана с использованием метода SFT (Supervised Fine-Tuning). Мы использовали синтетический датасет GrandMaster-PRO-MAX (150k инструкций), применяя подход CoT (Chain-Of-Thought) и промпты для GPT-4-turbo. Это позволило добиться высокой точности и когерентности ответов.
EN
Vikhr-Qwen-2.5-1.5B-Instruct was developed using the SFT (Supervised Fine-Tuning) method. The synthetic dataset GrandMaster-PRO-MAX (150k instructions) was used with CoT (Chain-Of-Thought) methodology and GPT-4-turbo prompts, enabling high accuracy and coherence in responses.
Пример кода для запуска / Sample code to run:
Рекомендуемая температура для генерации: 0.3 / Recommended generation temperature: 0.3 .
from transformers import AutoModelForCausalLM, AutoTokenizer
# Load the model and tokenizer
model_name = "Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Prepare the input text
input_text = "Напиши краткое описание книги Гарри Поттер."
messages = [
{"role": "system", "content": "Вы — Vikhr, ИИ помощник, созданный компанией Vikhr models для предоставления полезной, честной и безопасной информации."},
{"role": "user", "content": input_text},
]
# Tokenize and generate text
input_ids = tokenizer.apply_chat_template(messages, truncation=True, add_generation_prompt=True, return_tensors="pt")
output = model.generate(
input_ids,
max_length=1512,
temperature=0.3,
num_return_sequences=1,
no_repeat_ngram_size=2,
top_k=50,
top_p=0.95,
)
# Decode and print result
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
print(generated_text)
Ответ модели / Model response:
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.
Авторы / Authors
- Sergei Bratchikov, NLP Wanderer , Vikhr Team
- Nikolay Kompanets, LakoMoor , Vikhr Team
- Konstantin Korolev, Vikhr Team
- Aleksandr Nikolich, Vikhr Team
@inproceedings{nikolich2024vikhr,
title={Vikhr: Advancing Open-Source Bilingual Instruction-Following Large Language Models for Russian and English},
author={Aleksandr Nikolich and Konstantin Korolev and Sergei Bratchikov and Nikolay Kompanets and Igor Kiselev and Artem Shelmanov},
booktitle={Proceedings of the 4th Workshop on Multilingual Representation Learning (MRL) @ EMNLP-2024},
year={2024},
publisher={Association for Computational Linguistics},
url={https://arxiv.org/pdf/2405.13929}
}
Runs of Vikhrmodels Vikhr-Qwen-2.5-1.5B-Instruct on huggingface.co
471
Total runs
0
24-hour runs
12
3-day runs
81
7-day runs
113
30-day runs
More Information About Vikhr-Qwen-2.5-1.5B-Instruct huggingface.co Model
Url of Vikhr-Qwen-2.5-1.5B-Instruct
Vikhr-Qwen-2.5-1.5B-Instruct huggingface.co Url
Provider of Vikhr-Qwen-2.5-1.5B-Instruct huggingface.co
Other API from Vikhrmodels
Updated:October 25 2024
Total runs:
15.3K
Run Growth:
-3.2K
Growth Rate:
-20.65%
Total runs:
3.9K
Run Growth:
-10
Growth Rate:
-0.26%
Total runs:
1.9K
Run Growth:
328
Growth Rate:
16.87%
Total runs:
1.1K
Run Growth:
-172
Growth Rate:
-15.57%
Total runs:
943
Run Growth:
-75.7K
Growth Rate:
-8026.83%
Total runs:
879
Run Growth:
705
Growth Rate:
80.20%
Total runs:
865
Run Growth:
173
Growth Rate:
20.00%
Total runs:
829
Run Growth:
-50
Growth Rate:
-6.03%
Total runs:
620
Run Growth:
13
Growth Rate:
2.10%
Total runs:
611
Run Growth:
434
Growth Rate:
71.03%
Total runs:
526
Run Growth:
-127
Growth Rate:
-24.14%
Total runs:
507
Run Growth:
38
Growth Rate:
7.50%
Total runs:
459
Run Growth:
-124
Growth Rate:
-27.02%
Total runs:
443
Run Growth:
55
Growth Rate:
12.42%
Total runs:
427
Run Growth:
-534
Growth Rate:
-125.06%
Total runs:
358
Run Growth:
145
Growth Rate:
40.50%
Total runs:
292
Run Growth:
14
Growth Rate:
4.79%
Total runs:
253
Run Growth:
211
Growth Rate:
83.40%
Total runs:
250
Run Growth:
-183
Growth Rate:
-73.20%
Total runs:
241
Run Growth:
11
Growth Rate:
4.56%
Total runs:
226
Run Growth:
-104
Growth Rate:
-46.02%
Total runs:
163
Run Growth:
-746
Growth Rate:
-457.67%
Total runs:
155
Run Growth:
-26
Growth Rate:
-17.33%
Total runs:
121
Run Growth:
-63
Growth Rate:
-52.07%
Total runs:
107
Run Growth:
70
Growth Rate:
65.42%
Total runs:
105
Run Growth:
-6
Growth Rate:
-5.71%
Total runs:
102
Run Growth:
-25
Growth Rate:
-24.51%
Total runs:
102
Run Growth:
-810
Growth Rate:
-794.12%
Total runs:
100
Run Growth:
3
Growth Rate:
3.06%
Total runs:
95
Run Growth:
76
Growth Rate:
80.00%
Total runs:
91
Run Growth:
-25
Growth Rate:
-27.47%
Total runs:
89
Run Growth:
12
Growth Rate:
13.64%
Total runs:
85
Run Growth:
26
Growth Rate:
30.59%
Total runs:
83
Run Growth:
5
Growth Rate:
6.10%
Total runs:
83
Run Growth:
4
Growth Rate:
4.94%
Total runs:
78
Run Growth:
-27
Growth Rate:
-35.06%
Total runs:
78
Run Growth:
-16
Growth Rate:
-20.78%
Total runs:
77
Run Growth:
-13
Growth Rate:
-18.57%
Total runs:
74
Run Growth:
-5
Growth Rate:
-6.85%
Total runs:
74
Run Growth:
-7
Growth Rate:
-9.59%
Total runs:
74
Run Growth:
-4
Growth Rate:
-5.48%
Total runs:
72
Run Growth:
-2
Growth Rate:
-2.78%
Total runs:
72
Run Growth:
-7
Growth Rate:
-9.86%
Total runs:
72
Run Growth:
1
Growth Rate:
1.41%
Total runs:
71
Run Growth:
-10
Growth Rate:
-14.29%
Total runs:
71
Run Growth:
-2
Growth Rate:
-2.86%
Total runs:
70
Run Growth:
-12
Growth Rate:
-17.39%
Total runs:
66
Run Growth:
-5
Growth Rate:
-7.69%
Total runs:
62
Run Growth:
-6
Growth Rate:
-9.68%
Total runs:
61
Run Growth:
-26
Growth Rate:
-42.62%
Total runs:
61
Run Growth:
21
Growth Rate:
34.43%
Total runs:
60
Run Growth:
-10
Growth Rate:
-17.24%
Total runs:
57
Run Growth:
-10
Growth Rate:
-17.86%
Total runs:
52
Run Growth:
23
Growth Rate:
44.23%
Total runs:
42
Run Growth:
23
Growth Rate:
54.76%
Total runs:
39
Run Growth:
-63
Growth Rate:
-161.54%
Total runs:
29
Run Growth:
29
Growth Rate:
100.00%
Total runs:
27
Run Growth:
-1
Growth Rate:
-3.70%
Total runs:
27
Run Growth:
-4
Growth Rate:
-14.81%
Total runs:
26
Run Growth:
6
Growth Rate:
23.08%
Total runs:
25
Run Growth:
-2
Growth Rate:
-8.00%
Total runs:
24
Run Growth:
0
Growth Rate:
0.00%
Total runs:
23
Run Growth:
21
Growth Rate:
91.30%
Total runs:
20
Run Growth:
6
Growth Rate:
30.00%
Total runs:
19
Run Growth:
5
Growth Rate:
26.32%
Total runs:
14
Run Growth:
8
Growth Rate:
57.14%
Total runs:
14
Run Growth:
-7
Growth Rate:
-50.00%
Total runs:
14
Run Growth:
5
Growth Rate:
35.71%
Total runs:
13
Run Growth:
4
Growth Rate:
30.77%
Total runs:
12
Run Growth:
4
Growth Rate:
33.33%
Total runs:
12
Run Growth:
3
Growth Rate:
25.00%
Total runs:
11
Run Growth:
7
Growth Rate:
63.64%
Total runs:
10
Run Growth:
5
Growth Rate:
50.00%
Total runs:
9
Run Growth:
0
Growth Rate:
0.00%
Total runs:
9
Run Growth:
9
Growth Rate:
100.00%
Total runs:
9
Run Growth:
5
Growth Rate:
55.56%
Total runs:
8
Run Growth:
-14
Growth Rate:
-175.00%
Total runs:
8
Run Growth:
5
Growth Rate:
62.50%