Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,7 @@ Pretrained GPT-2 model on Finnish language using a causal language modeling (CLM
|
|
19 |
[this paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf)
|
20 |
and first released at [this page](https://openai.com/blog/better-language-models/).
|
21 |
|
22 |
-
**Note**: this model is quite small 117M parameter variant as in Huggingface's [GPT-2 config](https://huggingface.co/gpt2), so not the famous big 1.5B parameter variant by OpenAI. We also have bigger 345M parameter variant [gpt2-medium-finnish](https://huggingface.co/Finnish-NLP/gpt2-medium-finnish) available which
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
19 |
[this paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf)
|
20 |
and first released at [this page](https://openai.com/blog/better-language-models/).
|
21 |
|
22 |
+
**Note**: this model is quite small 117M parameter variant as in Huggingface's [GPT-2 config](https://huggingface.co/gpt2), so not the famous big 1.5B parameter variant by OpenAI. We also have bigger 345M parameter variant [gpt2-medium-finnish](https://huggingface.co/Finnish-NLP/gpt2-medium-finnish) and 774M parameter variant [gpt2-large-finnish](https://huggingface.co/Finnish-NLP/gpt2-large-finnish) available which perform better compared to this model.
|
23 |
|
24 |
## Model description
|
25 |
|