Update README.md

README.md

@@ -1,18 +1,32 @@
 ---
 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
+- 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-128-v3
+# 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 **2 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 **8192**. 
+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. 
 
-This is a base model and hasn't undergone any supervised finetuing yet.
+- It has **33.7 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