Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- ytu-ce-cosmos/gsm8k_tr
|
| 4 |
+
language:
|
| 5 |
+
- tr
|
| 6 |
+
base_model:
|
| 7 |
+
- Qwen/Qwen2-1.5B
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
+
---
|
| 10 |
+
# TR Qwen2-1.5B
|
| 11 |
+
* A new test of fine-tuning right after the first test version of [TR-Qwen2-7B](https://huggingface.co/Quardo/TR-Qwen2-7B)
|
| 12 |
+
* This time, everything is pretty much the same (half the learning-rate, though.)
|
| 13 |
+
* Fine-tuned on [Together AI](https://together.ai) with [GSM8K-Turkish by Yıldız Teknik Üniversitesi](https://huggingface.co/datasets/ytu-ce-cosmos/gsm8k_tr)'s dataset
|