Update README.md

README.md

@@ -8,6 +8,8 @@ tags:
 license: apache-2.0
 language:
 - en
+datasets:
+- Roman1111111/gemini-3.1-pro-hard-high-reasoning
 ---
 
 # Uploaded finetuned  model
@@ -15,7 +17,10 @@ language:
 - **Developed by:** Entity-27th
 - **License:** apache-2.0
 - **Finetuned from model :** unsloth/Qwen3.5-9B
+- **Hardware:** AMD Instinct MI300X x 1
 
 This qwen3_5 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 is a variant of Qwen3.5-9B, PEFT'd and distilled with gemini-3.1-pro-hard-high-reasoning dataset. Trained on a single MI300X GPU, Stellar Pro is designed to enhance the base model's reasoning capabilities via distillation from Gemini 3.1 Pro.