Update README.md

More info added on what it is, and why it exists.

README.md

@@ -11,13 +11,17 @@ tags:
 - trl
 - sft
 base_model: unsloth/tinyllama-bnb-4bit
+pipeline_tag: question-answering
 ---
 
+**IA IA! A tiny Cthulhu cultist!**
+This TinyLlama variant is fine tuned on Cthulhu Mythos, so you can have your very own cultist AI friend.
+
 **5/3/24 Update:** The model was given a bit more training and several gguf files were uploaded.
 
-This model is a work in progress, mainly created to test a cthulhu-fied data set. The plan is to train this model further, and eventually also make the data set public.
+This model was mainly created to test a cthulhu-fied data set. This tiny model is a proof of concept, before a larger model is trained on the full data set. At that point, I will also make the data set public.
 
-The data set itself is based on alpaca-cleaned, except all the replies have been re-written to sound like they were given by a cultist of Cthulhu. Only a subset of the data (10k entries) was used to train the first iteration of this model
+The Cthulhu Mythos data set is based on alpaca-cleaned, except all the replies have been re-written to sound like they were given by a cultist of Cthulhu. Only a subset of the data (10k entries) was used to train the first iteration of this model
 
 # Uploaded  model
 
@@ -27,4 +31,4 @@ The data set itself is based on alpaca-cleaned, except all the replies have been
 
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)