Update README.md

README.md

@@ -1,9 +1,7 @@
-
-# Fine tuning phi-2 large language model using QLORA.
-Key Features:
-phi-2 model. https://huggingface.co/microsoft/phi-2
-4-bit quantization using QLORA.
-Number of steps 1000.
-Trained on open assistant dataset. https://huggingface.co/datasets/OpenAssistant/oasst1
-Loss on training dataset 1.52.
-Hugging Face Spaces app:
+license: apache-2.0
+title: finetuning_llm_phi-2
+sdk: gradio
+emoji: 🏆
+colorFrom: green
+colorTo: yellow
+pinned: true