Update README.md

README.md

@@ -20,10 +20,16 @@ library_name: transformers
 This project uses Unsloth for fine-tuning. All training data is converted to OpenAI Harmony format before training, but there may be cases where the output format doesn't conform to the OpenAI Harmony specification.
 
 ## How I trained?
-We have actually trained the code and made it publicly available on GitHub. The code is published here solely as a reference to help you perform high-quality fine-tuning.
-
+We have actually trained the code and made it publicly available on GitHub. The code is published here solely as a reference to help you perform high-quality fine-tuning.  
+  
 **GitHub repo**: [midorin-Linux/gpt-oss-20b-Coding-Distill](https://github.com/midorin-Linux/gpt-oss-20b-Coding-Distill)
 
+## Do you want to use pre-trained model?
+You can download pre-trained data from HuggingFace.  
+  
+**Safetensors repo**: [midorin-Linux/gpt-oss-20b-Coding-Distill](https://huggingface.co/midorin-Linux/gpt-oss-20b-Coding-Distill/edit/main/README.md)  
+**GGUF repo**: In Preparation.
+
 ## Overview
 This project implements a sophisticated multi-phase fine-tuning pipeline for the GPT-OSS-20B model, leveraging conversation data from multiple state-of-the-art AI models to create a balanced, high-performance language model optimized for:
 
@@ -64,3 +70,5 @@ GPT-OSS-20B Base Model
      ├─ Layers: Upper Attention layers + MLP + Adapter
      └─ Goal: Fine-tune attention patterns if needed
 ```
+
+