Update README.md

README.md

@@ -3,8 +3,22 @@ library_name: transformers
 pipeline_tag: text-generation
 license: mit
 base_model:
-- ByteDance-Seed/Seed-Coder-8B-Base-bf16
+- ByteDance-Seed/Seed-Coder-8B-Reasoning
 ---
+# Seed-Coder-8B-Reasoning-exl2
+Original model: [Seed-Coder-8B-Reasoning-bf16](https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Reasoning-bf16) by [ByteDance Seed](https://huggingface.co/ByteDance-Seed)
+
+## Quants
+[4bpw h6 (main)](https://huggingface.co/cgus/Seed-Coder-8B-Reasoning-exl2/tree/main)  
+[4.5bpw h6](https://huggingface.co/cgus/Seed-Coder-8B-Reasoning-exl2/tree/4.5bpw-h6)  
+[5bpw h6](https://huggingface.co/cgus/Seed-Coder-8B-Reasoning-exl2/tree/5bpw-h6)  
+[6bpw h6](https://huggingface.co/cgus/Seed-Coder-8B-Reasoning-exl2/tree/6bpw-h6)  
+[8bpw h8](https://huggingface.co/cgus/Seed-Coder-8B-Reasoning-exl2/tree/8bpw-h8)  
+
+## Quantization notes
+Made with Exllamav2 0.2.9 dev with default dataset.  
+These quants can be used with RTX GPU (Windows) or RTX/ROCm (Linux) with TabbyAPI or Text-Generation-WebUI.  
+Ensure it fits your VRAM since RAM offloading isn't supported by Exllamav2 library.
 
 # Seed-Coder-8B-Reasoning-bf16
 
@@ -104,4 +118,4 @@ For detailed benchmark performance, please refer to our [📑 Technical Report](
 
 ## License
 
-This project is licensed under the MIT License. See the [LICENSE file](https://github.com/ByteDance-Seed/Seed-Coder/blob/master/LICENSE) for details.
+This project is licensed under the MIT License. See the [LICENSE file](https://github.com/ByteDance-Seed/Seed-Coder/blob/master/LICENSE) for details.