add quantized versions

README.md

@@ -54,6 +54,23 @@ parameters:
 dtype: bfloat16
 ```
 
+# Quantizationed versions
+
+Quantizationed versions of this model is available thanks to [TheBloke](https://hf.co/TheBloke).
+
+##### GPTQ
+
+- [TheBloke/Seraph-7B-GPTQ](https://huggingface.co/TheBloke/Seraph-7B-GPTQ)
+
+##### GGUF
+
+- [TheBloke/Seraph-7B-GGUF](https://huggingface.co/TheBloke/Seraph-7B-GGUF)
+
+##### AWQ
+
+- [TheBloke/Seraph-7B-AWQ](https://huggingface.co/TheBloke/Seraph-7B-AWQ)
+
+
 # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
 
 Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Seraph-7B)