Update README.md

README.md

@@ -16,13 +16,23 @@ Instruction-tuned version of SalesForce/Xgen-7b-8k-base. The model is open for <
 
 We expanded Open-instruct with additional commercially viable zero-shot COT datasets from Flan v2 to total of 140k instruct-prompt responses. <br>
 
+The model supports up to <b>8192 tokens </b>
+
+## License
+- <b>Commercially Viable </b>
+- The instruction datasets used for instruction tuning are open for commercial usage.
+- Language Model, ([Salesforce/xgen-7b-8k-base](https://huggingface.co/Salesforce/xgen-7b-8k-base)) is under apache-2.0
+- Dataset ([VMware/open-instruct](https://huggingface.co/datasets/VMware/open-instruct)) is under cc-by-sa-3.0
+
 
-<b>Open-instruct <br>
+## Datasets used for Fine-Tuning
 
-Open-instruct-v1
+### Open-instruct
+
+**Open-instruct-v1**
 - Mosaic/Dolly-HHRLHF + filtered  OASST1 - cc by 3.0 
 
-Subset of COT SUBMIX (FROM FLAN V2) Zeroshot examples
+**Subset of COT SUBMIX (FROM FLAN V2) Zeroshot examples**
 - ESNLI -  MIT 
 - ECQA  - CDLA 1.0 - Sharing
 - Strategy  - MIT
@@ -31,18 +41,6 @@ Subset of COT SUBMIX (FROM FLAN V2) Zeroshot examples
 - aqua  - MIT
 - qasc  - Apache 2.0
 
- <br>
-
-The model supports up to <b>8192 tokens </b>
-
-
-
-## License
-- <b>Commercially Viable </b>
-- The instruction datasets used for instruction tuning are open for commercial usage.
-- Language Model, ([Salesforce/xgen-7b-8k-base](https://huggingface.co/Salesforce/xgen-7b-8k-base)) is under apache-2.0
-- Dataset ([VMware/open-instruct](https://huggingface.co/datasets/VMware/open-instruct)) is under cc-by-sa-3.0
-
 
 
 ## Use in Transformers