update with gerpt2-large info
Browse files
README.md
CHANGED
@@ -11,6 +11,8 @@ license: mit
|
|
11 |
|
12 |
A small German GPT2.
|
13 |
|
|
|
|
|
14 |
See the [GPT2 model card](https://huggingface.co/gpt2) for considerations on limitations and bias. See the [GPT2 documentation](https://huggingface.co/transformers/model_doc/gpt2.html) for details on GPT2.
|
15 |
|
16 |
## Comparison to [dbmdz/german-gpt2](https://huggingface.co/dbmdz/german-gpt2)
|
@@ -20,7 +22,8 @@ I evaluated both GerPT2 and the other German GPT2, [dbmdz/german-gpt2](https://h
|
|
20 |
| | CC-100 (PPL) | Wikipedia (PPL) |
|
21 |
|-------------------|--------------|-----------------|
|
22 |
| dbmdz/german-gpt2 | 49.47 | 62.92 |
|
23 |
-
| GerPT2 |
|
|
|
24 |
| | | |
|
25 |
|
26 |
See the script `evaluate.py` in the [GerPT2 Github repository](https://github.com/bminixhofer/gerpt2) for the code.
|
|
|
11 |
|
12 |
A small German GPT2.
|
13 |
|
14 |
+
Also check out [GerPT2-large](https://huggingface.co/benjamin/gerpt2-large), a large version of this model.
|
15 |
+
|
16 |
See the [GPT2 model card](https://huggingface.co/gpt2) for considerations on limitations and bias. See the [GPT2 documentation](https://huggingface.co/transformers/model_doc/gpt2.html) for details on GPT2.
|
17 |
|
18 |
## Comparison to [dbmdz/german-gpt2](https://huggingface.co/dbmdz/german-gpt2)
|
|
|
22 |
| | CC-100 (PPL) | Wikipedia (PPL) |
|
23 |
|-------------------|--------------|-----------------|
|
24 |
| dbmdz/german-gpt2 | 49.47 | 62.92 |
|
25 |
+
| GerPT2 | 24.78 | 35.33 |
|
26 |
+
| GerPT2-large | 16.08 | 23.26 |
|
27 |
| | | |
|
28 |
|
29 |
See the script `evaluate.py` in the [GerPT2 Github repository](https://github.com/bminixhofer/gerpt2) for the code.
|