Update README.md

README.md

@@ -7,12 +7,12 @@ language:
 - id
 ---
 # 🦚Merak-7B-v3-Mini-Orca🐳
-
+<p align="center">
 <img src="https://i.imgur.com/39sQd3h.png" alt="Merak Orca" width="300" height="300"/>
+</p>
 
 **Merak-7B-v3-Mini-Orca** is Ichsan2895's [Merak-7B-v3](https://huggingface.co/Ichsan2895/Merak-7B-v3) fine-tuned on Bahasa Indonesia translated psmathur's [orca_mini_v1_dataset](https://huggingface.co/datasets/psmathur/orca_mini_v1_dataset).
 
-[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
 
 ## Usage
 This model fit on 16GB VRAM GPU (Google Collab T4 wil do), by using BitsandBytes it can run on 6GB VRAM GPU
@@ -42,6 +42,8 @@ USER: <prompt> (without the <>)
 ASSISTANT:
 ```
 ## Training details
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="100" height="16"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+
 Merak-7B-v3-Mini-Orca was instruction fine-tuned on 2 x 3090-24GB for 6 hours. [LoRA](https://github.com/microsoft/LoRA), [DeepSpeed ZeRO-2](https://github.com/microsoft/DeepSpeed), and [FlashAttention](https://github.com/Dao-AILab/flash-attention) were implemented during training using [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl).
 Hyperparameter | value |
 | ------ | ------ |