Update README.md

README.md

@@ -1,6 +1,10 @@
 ---
 license: llama2
 ---
+* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/speechless-mistral-7B-dare-0.85-AWQ)
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/speechless-mistral-7B-dare-0.85-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/speechless-mistral-7B-dare-0.85-GGUF)
+
 Experiment for DARE(Drop and REscale), most of the delta parameters can be directly set to zeros without affecting the capabilities of SFT LMs and larger models can tolerate a higher proportion of discarded parameters.
 
 Merged with below DARE models.