Update README.md
Browse files
README.md
CHANGED
|
@@ -1,9 +1,21 @@
|
|
| 1 |
---
|
| 2 |
widget:
|
| 3 |
-
- text:
|
| 4 |
example_title: Example 1
|
| 5 |
- text: በ ኢንግሊዝ ፕሪምየር ሊግ
|
| 6 |
example_title: Example 2
|
| 7 |
- text: ፕሬዚዳንት ዶናልድ ትራምፕ
|
| 8 |
example_title: Example 3
|
| 9 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
widget:
|
| 3 |
+
- text: አዲስ አበባ
|
| 4 |
example_title: Example 1
|
| 5 |
- text: በ ኢንግሊዝ ፕሪምየር ሊግ
|
| 6 |
example_title: Example 2
|
| 7 |
- text: ፕሬዚዳንት ዶናልድ ትራምፕ
|
| 8 |
example_title: Example 3
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# gpt2-small-amharic-128-v3
|
| 12 |
+
|
| 13 |
+
This is a smaller version of the [gpt2](https://huggingface.co/openai-community/gpt2) decoder transformer model pretrained from scratch for **1.5 days** on **290 million tokens** of **Amharic** text. The **context size** of this model is **128** tokens. It has the same tokenizer as gpt2, trained from scratch using the same dataset with a vocabulary size of **16384**.
|
| 14 |
+
|
| 15 |
+
This is a base model and hasn't undergone any supervised finetuing yet.
|
| 16 |
+
|
| 17 |
+
### Demo
|
| 18 |
+
|
| 19 |
+
You can use the following demo to generate text using this model. Please **enter a prompt** and click the **Generate** button to generate completions for the prompt.
|
| 20 |
+
|
| 21 |
+
https://huggingface.co/spaces/rasyosef/GPT2-Amharic
|