Update README.md

README.md

@@ -1,22 +1,25 @@
 ---
 tags:
-- generated_from_trainer
+- Question(s) Generation
 metrics:
 - rouge
 model-index:
-- name: anshoomehra/t5-v1-base-s2-auto-qgen
+- name: anshoomehra/question-generation-auto-t5-v1-base-s
   results: []
 ---
 
-# t5-v1-base-s2-auto-qgen
+# Auto Question Generation  
+The model is intended to be used for Auto Question Generation task i.e. no hint are required as input. The model is expected to produce one or possibly more than one question from the provided context.
+ 
+[Live Demo: Question Generation](https://huggingface.co/spaces/anshoomehra/question_generation)
 
-## Model description
+Including this there are four models trained with different training sets, demo provide comparison to all in one go. However, you can reach individual projects at below links:
 
-This model was fine-tuned from base t5 v1.1 on SQUAD2 for auto-question generation(i.e. without hints).
+[Auto Question Generation v2](https://huggingface.co/anshoomehra/question-generation-auto-t5-v1-base-s-q)
 
-## Intended uses & limitations
+[Auto/Hints based Question Generation v1](https://huggingface.co/anshoomehra/question-generation-auto-hints-t5-v1-base-s-q)
 
-The model is expected to produce one or possibly more than one question from provided context. If you are looking for model which receive hints as input or combination, these will be added soon and the link will be provided here: ##)
+[Auto/Hints based Question Generation v1](https://huggingface.co/anshoomehra/question-generation-auto-hints-t5-v1-base-s-q-c)
 
 This model can be used as below:
 
@@ -26,7 +29,7 @@ from transformers import (
     AutoTokenizer
 )
 
-model_checkpoint = "anshoomehra/t5-v1_1-base-squadV2AutoQgen"
+model_checkpoint = "anshoomehra/question-generation-auto-t5-v1-base-s"
 
 model = AutoModelForSeq2SeqLM.from_pretrained(model_checkpoint)
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -35,7 +38,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
 context="question_context: <context>"
 encodings = tokenizer.encode(context, return_tensors='pt', truncation=True, padding='max_length').to(device)
 
-## You can play with many hyperparams to condition the output
+## You can play with many hyperparams to condition the output, look at demo
 output = model.generate(encodings, 
                         #max_length=300, 
                         #min_length=20, 
@@ -46,7 +49,7 @@ output = model.generate(encodings,
                         #temperature=1.1
                        )
 
-## Multiple questions are expected to be delimited by </s>
+## Multiple questions are expected to be delimited by '?' You can write a small wrapper to elegantly format. Look at the demo.
 questions = [tokenizer.decode(id, clean_up_tokenization_spaces=False, skip_special_tokens=False) for id in output]
 ```
 
@@ -65,7 +68,7 @@ The following hyperparameters were used during training:
 - num_epochs: 10
 
 ### Training results
-Rouge metrics is heavily penalized because of multiple questions in target sample space.
+Rouge metrics is heavily penalized because of multiple questions in target sample space,
 
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|