Update README.md

README.md

@@ -1,8 +1,35 @@
 ---
 license: apache-2.0
+base_model: internlm/AlchemistCoder-DS-6.7B
 tags:
 - code generation
 ---
+
+# AlchemistCoder-DS-6.7B-exl2
+
+Original model: [AlchemistCoder-DS-6.7B](https://huggingface.co/internlm/AlchemistCoder-DS-6.7B)  
+Model creator: [internlm](https://huggingface.co/internlm)
+
+## Quants
+[4bpw h6](https://huggingface.co/cgus/AlchemistCoder-DS-6.7B-exl2/tree/main)  
+[4.25bpw h6](https://huggingface.co/cgus/AlchemistCoder-DS-6.7B-exl2/tree/4.25bpw-h6)  
+[4.65bpw h6](https://huggingface.co/cgus/AlchemistCoder-DS-6.7B-exl2/tree/4.65bpw-h6)  
+[5bpw h6](https://huggingface.co/cgus/AlchemistCoder-DS-6.7B-exl2/tree/5bpw-h6)  
+[6bpw h6](https://huggingface.co/cgus/AlchemistCoder-DS-6.7B-exl2/tree/6bpw-h6)  
+[8bpw h8](https://huggingface.co/cgus/AlchemistCoder-DS-6.7B-exl2/tree/8bpw-h8)
+## Quantization notes
+Made with Exllamav2 0.1.3 with the default dataset.
+## How to run
+This model is meant to be used with Exllamav2 loader that requires the model to be fully loaded into GPU VRAM.  
+It primarily requires a Nvidia RTX card on Windows/Linux or AMD card on Linux.  
+If you want to use this model but your system doesn't meet these requirements, you should look for GGUF versions of the model.  
+It can be used with such apps like:  
+[Text Generation Webui](https://github.com/oobabooga/text-generation-webui)  
+[KoboldAI](https://github.com/henk717/KoboldAI)  
+[ExUI](https://github.com/turboderp/exui)  
+[lollms-webui](https://github.com/ParisNeo/lollms-webui)
+# Original model card
+
 # AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data
 
 [[🤗 HuggingFace](https://huggingface.co/internlm/AlchemistCoder-DS-6.7B)]