Update README.md
Browse files
README.md
CHANGED
|
@@ -3,7 +3,7 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
---
|
| 5 |
|
| 6 |
-
# Ukrainian finetuned
|
| 7 |
|
| 8 |
<!-- Supervised finetuning of Mistral-7B-Instruct-v0.2 on ukrainian dataset-->
|
| 9 |
|
|
@@ -19,7 +19,12 @@ text = "[INST]Відповідайте лише буквою правильно
|
|
| 19 |
|
| 20 |
This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:
|
| 21 |
|
| 22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
## 💻 Usage
|
| 24 |
|
| 25 |
```python
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
---
|
| 5 |
|
| 6 |
+
# Ukrainian finetuned Mistral-7B-Instruct-v0.2
|
| 7 |
|
| 8 |
<!-- Supervised finetuning of Mistral-7B-Instruct-v0.2 on ukrainian dataset-->
|
| 9 |
|
|
|
|
| 19 |
|
| 20 |
This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:
|
| 21 |
|
| 22 |
+
## Model Architecture
|
| 23 |
+
This instruction model is based on Mistral-7B-v0.2, a transformer model with the following architecture choices:
|
| 24 |
+
- Grouped-Query Attention
|
| 25 |
+
- Sliding-Window Attention
|
| 26 |
+
- Byte-fallback BPE tokenizer
|
| 27 |
+
-
|
| 28 |
## 💻 Usage
|
| 29 |
|
| 30 |
```python
|