lighteternal
commited on
Commit
•
1a29179
1
Parent(s):
9fb63b5
Update README.md
Browse files
README.md
CHANGED
@@ -46,7 +46,8 @@ generator = pipeline(
|
|
46 |
|
47 |
text = "Μια φορά κι έναν καιρό"
|
48 |
|
49 |
-
print("\
|
|
|
50 |
text,
|
51 |
max_length=len(text.split(" "))+15,
|
52 |
do_sample=True,
|
@@ -75,5 +76,8 @@ This is a better version of our GPT-2 small model (https://huggingface.co/lighte
|
|
75 |
| Perplexity | 39.12 |
|
76 |
|
77 |
|
78 |
-
###
|
|
|
|
|
|
|
79 |
Based on the work of Thomas Dehaene (ML6): https://blog.ml6.eu/dutch-gpt2-autoregressive-language-modelling-on-a-budget-cff3942dd020
|
|
|
46 |
|
47 |
text = "Μια φορά κι έναν καιρό"
|
48 |
|
49 |
+
print("\
|
50 |
+
".join([x.get("generated_text") for x in generator(
|
51 |
text,
|
52 |
max_length=len(text.split(" "))+15,
|
53 |
do_sample=True,
|
|
|
76 |
| Perplexity | 39.12 |
|
77 |
|
78 |
|
79 |
+
### Acknowledgement
|
80 |
+
|
81 |
+
The research work was supported by the Hellenic Foundation for Research and Innovation (HFRI) under the HFRI PhD Fellowship grant (Fellowship Number:50, 2nd call)
|
82 |
+
|
83 |
Based on the work of Thomas Dehaene (ML6): https://blog.ml6.eu/dutch-gpt2-autoregressive-language-modelling-on-a-budget-cff3942dd020
|