Update README.md

README.md

@@ -15,11 +15,20 @@ It is the result of first merging the deltas from the above repository with the
 * [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/stable-vicuna-13B-GGML).
 * [Unquantised 16bit model in HF format](https://huggingface.co/TheBloke/stable-vicuna-13B-HF).
 
+## PROMPT TEMPLATE
+
+This model works best with the following prompt template:
+
+```
+### USER: your prompt here
+### ASSISTANT:
+```
+
 ## GIBBERISH OUTPUT IN `text-generation-webui`?
 
-Please read the Provided Files section below. You should use `wizardLM-7B-GPTQ-4bit-128g.no-act-order.safetensors` unless you are able to use the latest GPTQ-for-LLaMa code.
+Please read the Provided Files section below. You should use `stable-vicuna-13B-GPTQ-4bit.no-act-order.safetensors` unless you are able to use the latest GPTQ-for-LLaMa code.
 
-If you're using a text-generation-webui one click installer, you MUST use `wizardLM-7B-GPTQ-4bit-128g.no-act-order.safetensors`.
+If you're using a text-generation-webui one click installer, you MUST use `stable-vicuna-13B-GPTQ-4bit.no-act-order.safetensors`.
 
 ## Provided files