Update README.md

README.md

@@ -18,10 +18,17 @@ datasets:
 
 ## Description
 
-This model was developed for use in a competition.
+This model was developed for use in a competition, specifically for [松尾研大規模言語モデル講座2024](https://weblab.t.u-tokyo.ac.jp/lecture/course-list/large-language-model/).
 
 ## Uses
 
+```python
+!pip install unsloth
+!pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
+!pip install -U torch
+!pip install -U peft
+```
+
 ```python
 from unsloth import FastLanguageModel
 from peft import PeftModel
@@ -86,3 +93,8 @@ with open(f'./llm-jp-3-13b-it_lora_20241216_output.jsonl', 'w', encoding='utf-8'
 ### Training Procedure
 
 This model was fine-tuned using LoRA (Low-Rank Adaptation) to optimize training efficiency and minimize computational overhead while maintaining performance. The fine-tuning process utilized Japanese instruction data specifically designed for LLMs to enhance its capabilities in understanding and generating Japanese-language instructions.
+
+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)
+