42 lines
1009 B
Markdown
42 lines
1009 B
Markdown
|
|
---
|
||
|
|
license: mit
|
||
|
|
language:
|
||
|
|
- ru
|
||
|
|
tags:
|
||
|
|
- llama
|
||
|
|
- russian
|
||
|
|
- conversational
|
||
|
|
model-index:
|
||
|
|
- name: CalmaCatLM-2
|
||
|
|
results: []
|
||
|
|
library_name: transformers
|
||
|
|
model_creator: ViorikaAI
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
datasets:
|
||
|
|
- IlyaGusev/saiga_scored
|
||
|
|
- IlyaGusev/ru_turbo_alpaca
|
||
|
|
- OpenAssistant/oasst1
|
||
|
|
- OpenAssistant/oasst2
|
||
|
|
---
|
||
|
|
|
||
|
|
# 🐈⬛ CalmaCatLM-2-MINI
|
||
|
|
|
||
|
|
# Подробнее:
|
||
|
|
|
||
|
|
## ⚙️ Детали модели
|
||
|
|
- **Архитектура: LLama**
|
||
|
|
- **Параметры: 134M**
|
||
|
|
- **Язык: Русский**
|
||
|
|
- **Лицения: MIT**
|
||
|
|
|
||
|
|
## 🏋️ Детали Тренировки
|
||
|
|
- **Датасет:** saiga_scored, ru_turbo_alpaca, oasst 1 и 2 (RU часть)
|
||
|
|
- **Железо:** **ОДНА** NVIDIA **GEFORCE RTX 5060 TI** (16GB VRAM)
|
||
|
|
- **Эпохи:** 3
|
||
|
|
- **СРЕДНИЙ LOSS:** 2.3000
|
||
|
|
- **LR:** 5e-4
|
||
|
|
- **Контекст:** 4046 токенов
|
||
|
|
|
||
|
|
## 🛜 Наши Соц. Сети
|
||
|
|
- **Discord:** https://discord.gg/8JwTv8zj8d , https://discord.gg/7JE7maH6cf
|
||
|
|
- **Telegram:** https://t.me/viorika_official
|