Update readme

.gitattributes

@@ -6,3 +6,4 @@
 *.tar.gz filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -13,6 +13,9 @@ datasets:
 - cnn_dailymail
 metrics:
 - f1
+widget:
+- text: "q: Who is Elon Musk? a: an entrepreneur q: When was he born? c: Elon Musk is an entrepreneur born in 1971."
+- text: "emotion: I hope this works!"
 ---
 # T5 Base with QA + Summary + Emotion
 
@@ -32,6 +35,8 @@ Summarisation and emotion detection has not been evaluated yet.
 
 ### Question answering
 
+#### With Transformers
+
 ```python
 from transformers import T5ForConditionalGeneration, T5Tokenizer
 model = T5ForConditionalGeneration.from_pretrained("kiri-ai/t5-base-qa-summary-emotion")
@@ -54,8 +59,24 @@ context = "Elon Musk left OpenAI to avoid possible future conflicts with his rol
 print(get_answer("Why not?", [("Does Elon Musk still work with OpenAI", "No")], context)) # to avoid possible future conflicts with his role as CEO of Tesla
 ```
 
+#### With Kiri
+
+```python
+from kiri.models import T5QASummaryEmotion
+
+context = "Elon Musk left OpenAI to avoid possible future conflicts with his role as CEO of Tesla."
+prev_qa = [("Does Elon Musk still work with OpenAI", "No")]
+model = T5QASummaryEmotion()
+
+# Leave prev_qa blank for non conversational question-answering
+model.qa("Why not?", context, prev_qa=prev_qa)
+> "to avoid possible future conflicts with his role as CEO of Tesla"
+```
+
 ### Summarisation
 
+#### With Transformers
+
 ```python
 from transformers import T5ForConditionalGeneration, T5Tokenizer
 model = T5ForConditionalGeneration.from_pretrained("kiri-ai/t5-base-qa-summary-emotion")
@@ -69,8 +90,21 @@ def summary(context):
     return tokenizer.decode(tokens[0], skip_special_tokens=True)
 ```
 
+#### With Kiri
+
+```python
+from kiri.models import T5QASummaryEmotion
+
+model = T5QASummaryEmotion()
+
+model.summarise("Long text to summarise")
+> "Short summary of long text"
+```
+
 ### Emotion detection
 
+#### With Transformers
+
 ```python
 from transformers import T5ForConditionalGeneration, T5Tokenizer
 model = T5ForConditionalGeneration.from_pretrained("kiri-ai/t5-base-qa-summary-emotion")
@@ -83,3 +117,19 @@ def emotion(context):
             attention_mask=features['attention_mask'], max_length=64)
     return tokenizer.decode(tokens[0], skip_special_tokens=True)
 ```
+
+#### With Kiri
+
+```python
+from kiri.models import T5QASummaryEmotion
+
+model = T5QASummaryEmotion()
+
+model.emotion("I hope this works!")
+> "optimism"
+```
+
+## About us
+
+Kiri makes using state-of-the-art models easy, accessible and scalable.
+[Website](https://kiri.ai) | [Natural Language Engine](https://github.com/kiri-ai/kiri)