Update README.md

README.md

@@ -1,34 +1,28 @@
----
-license: apache-2.0
-language:
-- en
-tags:
-- about
-- NotLLM
-- fake
----
 # About Me - Akicou
 
-Hi, I'm **Akicou**, and I specialize in sharing **quantized Large Language Models (LLMs)** in **GGUF format**. These models are processed using my own service, **[GGUFORGE](https://gguforge.com)**, which focuses on converting raw models into GGUF format for easier and more efficient usage.
+Hi, I'm **Akicou**, and I specialize in sharing **quantized Large Language Models (LLMs)** in **GGUF format**. These models are processed using my own service, **[GGUFORGE](https://gguforge.com)**, which focuses on converting raw models into GGUF format for more efficient usage.
 
-## What I Do
+### ⚠️ Important Notes:
+- I **only verify** model outputs **after explicitly testing** them. If I haven't stated that a model works, I **cannot guarantee** its functionality in raw `safetensors` or any other format.
+- Models are **deleted within 5 days** of upload unless I consider them worth keeping.
+- My current goal is to **reduce large SOTA models** while maintaining their quality and avoiding garbage output. This is still a learning process, and I'm constantly experimenting with new methods to improve results.
 
-- I post models and their **GGUF-converted versions** via [gguforge.com](https://gguforge.com), a platform I created for quantizing LLMs.
-- I **test and verify** model outputs only when I explicitly state that a model **works**. If I haven't personally verified it, I can't guarantee the model's performance — especially when using raw safetensors.
-- To keep my repositories clean and efficient, I **delete models within 5 days** of upload unless they prove to be valuable and worth keeping.
-- My ongoing mission is to **reduce the size of large SOTA (State-of-the-Art) models** while maintaining their functionality and ensuring they **don’t produce garbage output**. As this is a complex and evolving process, I'm constantly experimenting with new methods and techniques.
+---
 
-## About GGUFORGE
+## 🧰 About GGUFORGE (My GGUF Conversion Service)
 
-**GGUFORGE** is a self-hosted platform where users can log in via **Hugging Face OAuth** and request conversions of models into GGUF format.
+**[GGUFORGE](https://gguforge.com)** is a self-hosted platform where users can:
+- Log in via **Hugging Face OAuth**
+- Request **model to GGUF conversions**
 
-### Key Info:
-- **No Guarantees on Speed**: Since the service is self-hosted, processing speed may vary. I’ll do my best to fulfill requests as quickly as possible.
-- **Model Quality**: If a converted GGUF model produces poor results, it's likely due to the **original model's training or fine-tuning**, not the GGUF conversion process itself.
-- **Request Policy**: I may deny conversion requests if there are already **many GGUF versions** of the same model available.
-- **Self-Host Option**: If you prefer to run the conversion yourself, feel free to use the open-source tool I created: [automaticConversion GitHub repo](https://github.com/Akicuo/automaticConversion)
+### 📌 Important Information:
+- **Speed**: I cannot guarantee fast processing due to self-hosting constraints, but I aim to handle requests as soon as possible.
+- **Model Quality**: If the GGUF output performs poorly, it's likely due to the original model's training or fine-tuning, **not the GGUF conversion process**.
+- **Request Approval**: I may deny requests if similar GGUFs are already widely available.
+- **Uptime & Data**: I cannot guarantee 100% uptime. The database may reset as I experiment with different hosting providers. However, if your request is lost, I will restore it manually.
+- **Self-Hosting**: You're welcome to host GGUFORGE yourself using the source code:  
+  [https://github.com/Akicuo/automaticConversion](https://github.com/Akicuo/automaticConversion)
 
 ---
 
-Thanks for stopping by, and happy quantizing!
-— **Akicou**
+Thank you for visiting, and I hope you find the models and tools I share useful!