Update README.md

README.md

@@ -23,6 +23,10 @@ tags:
 </div>
 <!-- header end -->
 
+# Llama2 70b Guanaco QLoRA - fp16
+- Model creator: [Mikael110](https://huggingface.co/Mikael110)
+- Original model: [Llama2 70b Guanaco QLoRA](https://huggingface.co/Mikael110/llama-2-70b-guanaco-qlora)
+  
 # Mikael110's Llama2 70b Guanaco QLoRA fp16
 
 These files are pytorch format fp16 model files for [Mikael110's Llama2 70b Guanaco QLoRA](https://huggingface.co/Mikael110/llama-2-70b-guanaco-qlora).
@@ -32,8 +36,9 @@ It is the result of merging and/or converting the source repository to float16.
 ## Repositories available
 
 * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/llama-2-70b-Guanaco-QLoRA-GPTQ)
-* [Merged fp16 model in pytorch model format for GPU inference and further conversions](https://huggingface.co/TheBloke/llama-2-70b-Guanaco-QLoRA-fp16)
-* [Original QLoRA model](https://huggingface.co/Mikael110/llama-2-70b-guanaco-qlora)
+* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/llama-2-70b-Guanaco-QLoRA-GGML)
+* [Merged fp16 model, for GPU inference and further conversions](https://huggingface.co/TheBloke/llama-2-70b-Guanaco-QLoRA-fp16)
+* [Mikael110's original QLoRA adapter](https://huggingface.co/Mikael110/llama-2-70b-guanaco-qlora)
 
 ## Prompt template: Guanaco