Update README.md

README.md

@@ -1,21 +1,24 @@
 ---
-base_model: unsloth/gemma-3-27b-it-unsloth-bnb-4bit
+base_model:
+- unsloth/gemma-3-27b-it-unsloth-bnb-4bit
 tags:
 - text-generation-inference
 - transformers
 - unsloth
 - gemma3
-license: apache-2.0
+- CoT
+license: mpl-2.0
 language:
 - en
+datasets:
+- Jackrong/Natural-Reasoning-gpt-oss-120B-S1
 ---
 
-# Uploaded finetuned  model
-
+# HomeGem4Bn
 - **Developed by:** TitleOS
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/gemma-3-27b-it-unsloth-bnb-4bit
+- **License:** mpl-2.0
+- **Finetuned from model :** unsloth/gemma-3n-e4b-it-unsloth-bnb-4bit
 
-This gemma3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+### MindGem 27B is a finetuned QLoRA adapter for google/gemma-3-27b-it, designed to imbue chain of thought and an internal monologue to Gemma 3 27B. Finetuning was performed on an A100 SXM4, using the Jackrong/Natural-Reasoning-gpt-oss-120B-S1 dataset.
 
-[<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)