Initial GPTQ model commit

README.md

@@ -42,7 +42,7 @@ GGML versions are not yet provided, as there is not yet support for SuperHOT in
 ## Repositories available
 
 * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Vicuna-13B-1.3.0-SuperHOT-8K-GPTQ)
-* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/%%REPO_FP16%%)
+* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Vicuna-13B-1.3.0-SuperHOT-8K-fp16)
 * [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/lmsys/vicuna-13b-v1.3)
 
 ## How to easily download and use this model in text-generation-webui with ExLlama