Update README.md

README.md

@@ -2,23 +2,33 @@
 base_model: Qwen/Qwen2.5-7B-Instruct
 library_name: peft
 pipeline_tag: text-generation
+language:
+- en
+tags:
+- persona
+- llm
 ---
 
 # Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
-
-
+I developed a persona LLM, also known as a role-play LLM.
+The character is modeled after Megumin, a character from the novel Blessing of this Wonderful World.
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
-
+This model is fine-tuned using the Qwen/Qwen2.5-7B-Instruct model as a mother model.
+Due to the lack of GPU memory and resources, we used the QLoRA method to train only certain layer parts.
+The learning factors were as follows
 
+- learning_rate=5e-5
+- lr_scheduler_type="cosine"
+- warmup_steps=800
+- num_train_epochs=5
+- per_device_train_batch_size=8
 
-- **Developed by:** [More Information Needed]
+- **Developed by:** [Junhoee Ku](https://github.com/junhoeKu)
 - **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
 - **Model type:** [More Information Needed]