Edit model card

Fialka v3.0 7B

Violet

Description

Fialka language models are trained to follow instructions and maintain communication in Russian. The third version of the model was based on the Llama 2 model, which was specifically trained on a large corpus of Russian, allowing Fialka to generate its responses more accurately.

Usage

The model has a query format as in zephyr.

<|user|>
Что такое мем?</s>
<|assistant|>
Мем - это культурный феномен, который может быть описан как информационный вирус. Он представляет собой абстрактный элемент культуры или идеи в виде изображения (обычно с изображением человека) и его краткого текста на основе которого можно создать мемы различных форматов: от графических до текстовых шуток; мема могут использоваться для передачи определенных идей через интернет-сообщество без необходимости использовать слова напрямую!</s>

Check out the space to use the model in UI without downloading.

Downloads last month
13
Safetensors
Model size
6.74B params
Tensor type
F32
·
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train 0x7o/fialka-7B-v3

Collection including 0x7o/fialka-7B-v3