Commit
•
a3c0d6c
1
Parent(s):
ccf68f4
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@ In this repository I release GPT-2 model, that was trained on various texts for
|
|
| 4 |
|
| 5 |
The model is meant to be an entry point for fine-tuning on other texts.
|
| 6 |
|
| 7 |
-
|
| 8 |
|
| 9 |
I used a Turkish corpora that is taken from oscar-corpus.
|
| 10 |
|
|
@@ -14,7 +14,7 @@ With the Tokenizers library, I created a 52K byte-level BPE vocab based on the t
|
|
| 14 |
|
| 15 |
After creating the vocab, I could train the GPT-2 for Turkish on two 2080TI over the complete training corpus (five epochs).
|
| 16 |
|
| 17 |
-
|
| 18 |
|
| 19 |
The model itself can be used in this way:
|
| 20 |
|
|
@@ -33,3 +33,6 @@ pipe = pipeline('text-generation', model="redrussianarmy/gpt2-turkish-cased",
|
|
| 33 |
text = pipe("Akşamüstü yolda ilerlerken, ")[0]["generated_text"]
|
| 34 |
print(text)
|
| 35 |
```
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
|
| 5 |
The model is meant to be an entry point for fine-tuning on other texts.
|
| 6 |
|
| 7 |
+
## Training corpora
|
| 8 |
|
| 9 |
I used a Turkish corpora that is taken from oscar-corpus.
|
| 10 |
|
|
|
|
| 14 |
|
| 15 |
After creating the vocab, I could train the GPT-2 for Turkish on two 2080TI over the complete training corpus (five epochs).
|
| 16 |
|
| 17 |
+
## Using the model
|
| 18 |
|
| 19 |
The model itself can be used in this way:
|
| 20 |
|
|
|
|
| 33 |
text = pipe("Akşamüstü yolda ilerlerken, ")[0]["generated_text"]
|
| 34 |
print(text)
|
| 35 |
```
|
| 36 |
+
|
| 37 |
+
## Contact (Bugs, Feedback, Contribution and more)
|
| 38 |
+
For questions about the GPT2-Turkish model, just open an issue [here](https://github.com/redrussianarmy/gpt2-turkish/issues) 🤗
|