|
--- |
|
widget: |
|
- text: አዲስ አበባ |
|
example_title: Example 1 |
|
- text: በ ኢንግሊዝ ፕሪምየር ሊግ |
|
example_title: Example 2 |
|
- text: ፕሬዚዳንት ዶናልድ ትራምፕ |
|
example_title: Example 3 |
|
language: |
|
- am |
|
metrics: |
|
- perplexity |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# gpt2-small-amharic-8k-128-v3 |
|
|
|
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. |
|
|
|
- It has **29.5 Million parameters** |
|
- 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 **8192**. |
|
- This is a base model and hasn't undergone any supervised finetuing yet. |
|
|
|
It achieves the following results on the evaluation set: |
|
|
|
- `Loss: 3.59` |
|
- `Perplexity: 36.23` |
|
|
|
### Demo |
|
|
|
You can use the following demo to generate text using gpt2-small-amharic. Please **enter a prompt** and click the **Generate** button to generate completions for the prompt. |
|
|
|
https://huggingface.co/spaces/rasyosef/GPT2-Amharic |