Update

README.md

@@ -173,18 +173,50 @@ print(tokenizer.decode(output[0][input_len:]))
 ```
 
 Other tasks (e.g translation, classification etc) typically have 2 tags. The first signifies the kind/type of task and the second signifies the end of the input, prompting the model to begin generation. They are as follows:
-- Translation : ```python<translate> <yor>, <translate> .... <ibo>, <translate> ... <hau>```
-- Instruction following: ```python <prompt><response>```
-- Sentiment Analysis: ```python <classify> .... <sentiment>```
-- Topic Classification: ```python <classify> .... <sentiment>```
-- Text summarization : ```python <summarize> ... <summary>```
-- Headline Generation:```python <topic>... <headline>```
-- Text Diacritization: ```python <diacritize>.... <yor>```
-- Question answering: ```python <qa> <context>..... <question> .... <options>...<answer> OR <qa> <context> .... <answer> OR <prompt> Context:... Question:... <response>```
-- Named Entity Recognition: ```python <NER>.... <tag>```
-- Text cleaning: ```python<clean>...<correct>```
-
-You should typically put user's input between these 2 tags.
+- Translation
+  ```python
+  <translate> <yor>, <translate> .... <ibo>, <translate> ... <hau>
+  ```
+- Instruction following
+  ```python
+   <prompt><response>
+  ```
+- Sentiment Analysis
+  ```python
+   <classify> .... <sentiment>
+  ```
+- Topic Classification
+  ```python
+   <classify> .... <topic>
+  ```
+- Text summarization
+  ```python
+  <summarize> ... <summary>
+  ```
+- Headline Generation
+  ```python
+  <topic>... <headline>
+  ```
+- Text Diacritization
+  ```python
+   <diacritize>.... <yor>
+  ```
+- Question answering
+  ```python
+  <qa> <context>..... <question> .... <options>...<answer> or <qa> <context> .... <answer> or \
+  # The below were noted to work better.
+  <prompt> Context:... Question:... <response> or <prompt> Context:... Question:... Option A. Option B. ... <response> or <prompt> Context_question_options here <response>
+  ```
+- Named Entity Recognition
+  ```python
+   <NER>.... <tag>
+  ```
+- Text cleaning
+   ```python
+   <clean>...<correct>
+  ```
+
+You should typically put user's input between these 2 tags. Currently, model also doesnt perform very well on NER due to the scarce data on this.
 
 ## Training Details