Update README.md

README.md

@@ -85,30 +85,38 @@ into a single file, using the same order.
 
 ## Prompting
 
-Prompt template:
+Command-line instruction template:
 
 ```
-<BOS_TOKEN>
+./aya-23-8B.Q8_0.llamafile --log-disable --silent-prompt -p '<BOS_TOKEN>
 <|START_OF_TURN_TOKEN|>
-<|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|>
+<|USER_TOKEN|>Who is the president?<|END_OF_TURN_TOKEN|>
 <|START_OF_TURN_TOKEN|>
-<|CHATBOT_TOKEN|>
+<|CHATBOT_TOKEN|>'
 ```
 
-Command-line instruction template:
+"Prompt Template" for web GUI interface:
 
 ```
-./aya-23-8B.Q8_0.llamafile -p '<BOS_TOKEN>
+<BOS_TOKEN>
+<|SYSTEM_TOKEN|>{{prompt}}<|END_OF_TURN_TOKEN|>
+{{history}}
 <|START_OF_TURN_TOKEN|>
-<|USER_TOKEN|>Who is the president?<|END_OF_TURN_TOKEN|>
+<|CHATBOT_TOKEN|>
+```
+
+"Chat history template" for web GUI interface:
+
+```
 <|START_OF_TURN_TOKEN|>
-<|CHATBOT_TOKEN|>'
+<|USER_TOKEN|>{{message}}<|END_OF_TURN_TOKEN|>
 ```
 
 The maximum context size of this model is 8192 tokens. These llamafiles
 use a default context size of 512 tokens. Whenever you need the maximum
 context size to be available with llamafile for any given model, you can
-pass the `-c 0` flag.
+pass the `-c 0` flag. The temperature on these llamafiles is set to zero
+by default, because it helps. This can be changed, e.g. `--temp 0.8`.
 
 ## License