Set library name and pipeline tag

This PR ensures the "how to use" button appears on the top right, and sets the appropriate pipeline tag, ensuring people can find the model at https://huggingface.co/models?pipeline_tag=text-generation.

It also adds a link to the code repository.

README.md

@@ -1,11 +1,14 @@
 ---
+base_model:
+- meta-llama/Llama-2-7b-hf
 datasets:
 - hamishivi/rds-sels-multitask-rrmax-top326k
 language:
 - en
-base_model:
-- meta-llama/Llama-2-7b-hf
+pipeline_tag: text-generation
+library_name: transformers
 ---
+
 # RDS+ Multitask Tulu 2 326k
 
 This is a model trained on 326k samples selected by RDS+ for multiple tasks at once from the [Tulu 2 unfiltered dataset](https://huggingface.co/datasets/hamishivi/tulu-2-unfiltered).