Update README.md

README.md

@@ -1,22 +1,27 @@
 ---
 language:
 - en
-license: apache-2.0
+license: cc-by-nc-4.0
 tags:
 - text-generation-inference
 - transformers
 - unsloth
 - mistral
-- trl
+- GEB
 base_model: ammarali32/multi_verse_model
+datasets:
+- maldv/crabcanon
 ---
 
-# Uploaded  model
+# SHRDFU-7b Δ
 
 - **Developed by:** maldv
-- **License:** apache-2.0
-- **Finetuned from model :** ammarali32/multi_verse_model
+- **License:** cc-by-nc-4.0
+- **Finetuned from model:** ammarali32/multi_verse_model
+- **Methodology:** Peft to train; extending intelligence and problem solving w/ crabcanon
 
-This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+As I work on understanding how to layer information in to the model, this model used no conditioning and even with low LR's, had quite a sharp graph.  It definitely inherited the style of the source.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+I had been experimenting in this series with wrapping each paragraph or turn with `<s></s>` bos/eos tokens.  This may be semi-compatible with instruct, but is incompatible with alpaca and chatml.  Good to know. 
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="50"/>](https://github.com/unslothai/unsloth)