Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,7 @@ license: apache-2.0
|
|
| 5 |
|
| 6 |
# Ukrainian finetuned Mistral-7B-Instruct-v0.2
|
| 7 |
|
| 8 |
-
|
| 9 |
|
| 10 |
|
| 11 |
## Instruction format
|
|
@@ -24,7 +24,15 @@ This instruction model is based on Mistral-7B-v0.2, a transformer model with the
|
|
| 24 |
- Grouped-Query Attention
|
| 25 |
- Sliding-Window Attention
|
| 26 |
- Byte-fallback BPE tokenizer
|
| 27 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
## 💻 Usage
|
| 29 |
|
| 30 |
```python
|
|
|
|
| 5 |
|
| 6 |
# Ukrainian finetuned Mistral-7B-Instruct-v0.2
|
| 7 |
|
| 8 |
+
Supervised finetuning of Mistral-7B-Instruct-v0.2 on ukrainian datasets.
|
| 9 |
|
| 10 |
|
| 11 |
## Instruction format
|
|
|
|
| 24 |
- Grouped-Query Attention
|
| 25 |
- Sliding-Window Attention
|
| 26 |
- Byte-fallback BPE tokenizer
|
| 27 |
+
|
| 28 |
+
## Datasets
|
| 29 |
+
- [UA-SQUAD](https://huggingface.co/datasets/FIdo-AI/ua-squad/resolve/main/ua_squad_dataset.json)
|
| 30 |
+
- [Ukrainian StackExchange](https://huggingface.co/datasets/zeusfsx/ukrainian-stackexchange)
|
| 31 |
+
- [UAlpaca Dataset](https://github.com/robinhad/kruk/blob/main/data/cc-by-nc/alpaca_data_translated.json)
|
| 32 |
+
- [Ukrainian Subset from Belebele Dataset](https://github.com/facebookresearch/belebele)
|
| 33 |
+
- [Ukrainian Subset from XQA](https://github.com/thunlp/XQA)
|
| 34 |
+
- TODO - Ukrainian Subset from MKQA
|
| 35 |
+
|
| 36 |
## 💻 Usage
|
| 37 |
|
| 38 |
```python
|