Update README.md

README.md

@@ -4,36 +4,58 @@ tags:
 metrics:
 - rouge
 model-index:
-- name: t5-v1-base-s-q-auto-qgen
+- name: anshoomehra/question-generation-auto-t5-v1-base-s-q
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# 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)
 
-# t5-v1-base-s-q-auto-qgen
+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 is a fine-tuned version of [t5-v1-base](google/t5-v1_1-base) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 2.0511
-- Rouge1: 0.2149
-- Rouge2: 0.1011
-- Rougel: 0.1936
-- Rougelsum: 0.2014
+[Auto Question Generation v1](https://huggingface.co/anshoomehra/question-generation-auto-t5-v1-base-s)
 
-## Model description
+[Auto/Hints based Question Generation v1](https://huggingface.co/anshoomehra/question-generation-auto-hints-t5-v1-base-s-q)
 
-More information needed
+[Auto/Hints based Question Generation v2](https://huggingface.co/anshoomehra/question-generation-auto-hints-t5-v1-base-s-q-c)
 
-## Intended uses & limitations
+This model can be used as below:
 
-More information needed
+```
+from transformers import (
+    AutoModelForSeq2SeqLM,
+    AutoTokenizer
+)
 
-## Training and evaluation data
+model_checkpoint = "anshoomehra/question-generation-auto-t5-v1-base-s-q"
+
+model = AutoModelForSeq2SeqLM.from_pretrained(model_checkpoint)
+tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
+
+## Input with prompt
+context="question_context: <context>"
+encodings = tokenizer.encode(context, return_tensors='pt', truncation=True, padding='max_length').to(device)
 
-More information needed
+## You can play with many hyperparams to condition the output, look at demo
+output = model.generate(encodings, 
+                        #max_length=300, 
+                        #min_length=20, 
+                        #length_penalty=2.0, 
+                        num_beams=4,
+                        #early_stopping=True,
+                        #do_sample=True,
+                        #temperature=1.1
+                       )
+
+## 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]
+```
+
+## Training and evaluation data
 
-## Training procedure
+Custom data.
 
 ### Training hyperparameters