Commit
•
a14b29e
1
Parent(s):
fff9da4
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,4 +25,8 @@ The fine-tuning took 1 hour on a single RTX 4090 with the following hyperparamet
|
|
| 25 |
|
| 26 |
During the training of the adapter, the instruction format was maintained. Each prompt should be surrounded by `[INST]` and `[\INST]` tokens to leverage instruction fine-tuning.
|
| 27 |
|
| 28 |
-
This adapter allows the model to speak Polish more accurately than vanilla [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
During the training of the adapter, the instruction format was maintained. Each prompt should be surrounded by `[INST]` and `[\INST]` tokens to leverage instruction fine-tuning.
|
| 27 |
|
| 28 |
+
This adapter allows the model to speak Polish more accurately than vanilla [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1).
|
| 29 |
+
|
| 30 |
+
<p align="center">
|
| 31 |
+
<img src="https://huggingface.co/Azurro/Mistral-7B-Instruct-v0.1-qlora-polish/raw/main/mistral-7b-instruct-qlora-pl.jpg">
|
| 32 |
+
</p>
|