Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,75 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- Qwen/Qwen2.5-1.5B-Instruct
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
tags:
|
| 7 |
+
- conversational
|
| 8 |
+
- Furry
|
| 9 |
+
- merge
|
| 10 |
+
- LoRA
|
| 11 |
+
---
|
| 12 |
+
<h1 align="center">
|
| 13 |
+
<strong>FluffyTail</strong>
|
| 14 |
+
</h1>
|
| 15 |
+
|
| 16 |
+
<div align="center">
|
| 17 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6857f0290a176547a7b8c42c/JY18U5ax9f_wm64CeuNP-.png" alt="Main Model Illustration" width="350" />
|
| 18 |
+
</div>
|
| 19 |
+
|
| 20 |
+
<p align="center">
|
| 21 |
+
<em>Тёплый и эмоциональный ассистент с пушистым характером</em><br>
|
| 22 |
+
<em>A warm and emotional assistant with a fluffy personality</em>
|
| 23 |
+
</p>
|
| 24 |
+
|
| 25 |
+
## 🚀 Быстрый старт / Quick Start
|
| 26 |
+
|
| 27 |
+
Самый простой способ начать — использовать готовое решение через **Ollama**:
|
| 28 |
+
|
| 29 |
+
```bash
|
| 30 |
+
ollama run MarkProMaster229/FluffyTail
|
| 31 |
+
```
|
| 32 |
+
|
| 33 |
+
## 📖 Об обучении / Training Details
|
| 34 |
+
Модель была дообучена с использованием адаптера **LoRA** (Low-Rank Adaptation).
|
| 35 |
+
Количество обучаемых параметров: **9 232 384**, что составляет **~0.59%** от общего числа параметров базовой модели.
|
| 36 |
+
|
| 37 |
+
This model was fine-tuned using the **LoRA** (Low-Rank Adaptation) adapter.
|
| 38 |
+
Number of trainable parameters: **9,232,384**, which is **~0.59%** of the total parameters of the base model.
|
| 39 |
+
|
| 40 |
+
---
|
| 41 |
+
|
| 42 |
+
## ❓ Вопросы и благодарности / Q&A & Acknowledgments
|
| 43 |
+
|
| 44 |
+
<div style="display: flex; justify-content: space-between; align-items: flex-start; margin-top: 20px; margin-bottom: 20px; gap: 30px;">
|
| 45 |
+
<div style="flex: 1;">
|
| 46 |
+
<h3>Тут есть что-то ещё? 🤔</h3>
|
| 47 |
+
<p><strong>Конечно! Благодарности.</strong></p>
|
| 48 |
+
<p>Эта модель основана на работе команды Qwen и распространяется под оригинальной лицензией Apache 2.0.</p>
|
| 49 |
+
<div style="font-size: 0.9em; color: #afa6a6; margin-top: 10px; line-height: 1.4;">
|
| 50 |
+
<strong>Is there something else here? 🤔</strong><br>
|
| 51 |
+
<strong>Of course! Acknowledgments.</strong><br>
|
| 52 |
+
This model is based on the work of the Qwen Team and is distributed under the original Apache 2.0 license.
|
| 53 |
+
</div>
|
| 54 |
+
</div>
|
| 55 |
+
|
| 56 |
+
<div style="flex-shrink: 0; text-align: center;">
|
| 57 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6857f0290a176547a7b8c42c/k3FYAtJjspMDh4JLLZGQW.png"
|
| 58 |
+
alt="Иллюстрация для раздела вопросов"
|
| 59 |
+
width="250"
|
| 60 |
+
style="border-radius: 10px;" />
|
| 61 |
+
<p style="margin-top: 8px; font-size: 0.9em; color: #666; font-style: italic;">
|
| 62 |
+
Напоминание о важности признания чужого труда<br>
|
| 63 |
+
A reminder of the importance of acknowledging others' work
|
| 64 |
+
</p>
|
| 65 |
+
</div>
|
| 66 |
+
</div>
|
| 67 |
+
|
| 68 |
+
## 📚 Acknowledgements & Citation
|
| 69 |
+
|
| 70 |
+
This model is based on the following work:
|
| 71 |
+
|
| 72 |
+
- **Qwen2.5-1.5B-Instruct** by the Qwen Team.
|
| 73 |
+
- The original Apache 2.0 license for the base model applies.
|
| 74 |
+
|
| 75 |
+
If you use this model in your research, please consider citing the original Qwen2.5 work.
|