Update README.md

README.md

@@ -4,20 +4,25 @@ tags:
 - text-generation-inference
 - transformers
 - unsloth
-- llama
+- Phi-3
 - trl
 - sft
-license: apache-2.0
+- qwq
+- reasoning
+license: mit
 language:
 - en
+pipeline_tag: text-generation
 ---
 
+Phi-4 that has been tuned to be more advanced at reasoning. Parm2 magic 😉
+
+Unlike other Parm models we had to optimize out fine tuning process to ensure accuracy while still being able to release this model. **Training loss: 0.443800**
+
 # Uploaded  model
 
 - **Developed by:** Pinkstack
-- **License:** apache-2.0
+- **License:** MIT
 - **Finetuned from model :** unsloth/phi-4-unsloth-bnb-4bit
 
-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)
+This phi-4 model was trained with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.