Update README.md

README.md

@@ -30,6 +30,14 @@ This modelcard aims to be a base template for new models. It has been generated
 
 <!-- Provide a longer summary of what this model is. -->
 
+This model, lee12ki/llama2-finetune-7b, is a fine-tuned version of NousResearch/Llama-2-7b-chat-hf. It has been optimized for text-generation tasks, particularly for instruction-following and conversational applications. The fine-tuning was performed using the Guanaco-LLaMA2-1K dataset, a high-quality dataset designed for aligning language models to human preferences.
+
+The fine-tuning process utilizes QLoRA (Quantized Low-Rank Adaptation), which enables efficient and memory-friendly training with 4-bit precision. LoRA configuration parameters include:
+
+LoRA rank (r): 64
+Alpha parameter: 16
+Dropout probability: 0.1
+
 
 
 - **Developed by:** lee12ki