Update README.md

README.md

@@ -16,12 +16,8 @@ datasets:
 - grimulkan/physical-reasoning
 ---
 
-# Uploaded  model
+# Llama3 8B Wordcel
 
-- **Developed by:** jspr
-- **License:** apache-2.0
-- **Finetuned from model :** meta-llama/Meta-Llama-3-8B
+Wordcel is a Llama3 fine-tune intended to be used as a mid-training checkpoint for more specific chat/RP/storywriting applications.
 
-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)
+It has been trained from Llama3 8B Base on a composite dataset that highlights reasoning, (uncensored) stories, classic literature, and assorted interpersonal intelligence tasks.