Update README.md

README.md

@@ -9,16 +9,11 @@ Experimenting with Dataset Quality to improve generations, TinyLlama is faster t
 Overview
 This model is meant to enhance adherence to provided context (e.g., for RAG applications) and reduce hallucinations, inspired by airoboros context-obedient question answer format.
 
----
-license: cc-by-4.0
----
-
-# Contextual DPO
-
 ## Overview
 
 The format for a contextual prompt is as follows:
 ```
+Contextual-Request:
 BEGININPUT
 BEGINCONTEXT
 [key0: value0]
@@ -34,6 +29,7 @@ ENDINSTRUCTION
 ```
 
 I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
+- `Contextual-Request:` - denotes the type of request pattern the model is to follow for consistency
 - `BEGININPUT` - denotes a new input block
 - `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
 - `ENDCONTEXT` - denotes the end of the metadata block for the current input
@@ -46,6 +42,7 @@ I know it's a bit verbose and annoying, but after much trial and error, using th
 
 Here's a trivial, but important example to prove the point:
 ```
+Contextual-Request:
 BEGININPUT
 BEGINCONTEXT
 date: 2021-01-01
@@ -60,6 +57,7 @@ ENDINSTRUCTION
 
 And the expected response:
 ```
+### Contextual Response:
 Blueberries are now green.
 Source:
 date: 2021-01-01