Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,7 @@ A fine-tuned GPT-2 model (medium version, ~354.8 M parameters) for generating re
|
|
12 |
|
13 |
# How to use
|
14 |
|
15 |
-
The model is based on the [gpt2-medium-danish model](https://huggingface.co/KennethTM/gpt2-medium-danish) and performs better than the smaller version ([gpt2-small-danish-review-response
|
16 |
|
17 |
Test the model using the pipeline from the [🤗 Transformers](https://github.com/huggingface/transformers) library:
|
18 |
|
|
|
12 |
|
13 |
# How to use
|
14 |
|
15 |
+
The model is based on the [gpt2-medium-danish model](https://huggingface.co/KennethTM/gpt2-medium-danish) and performs better than the smaller version ([gpt2-small-danish-review-response](https://huggingface.co/KennethTM/gpt2-small-danish-review-response)). Supervised fine-tuning is applied to adapt the model to generate responses to customer reviews in Danish. A prompting template is applied to the examples used for training (see the example below).
|
16 |
|
17 |
Test the model using the pipeline from the [🤗 Transformers](https://github.com/huggingface/transformers) library:
|
18 |
|