Update README.md

README.md

@@ -8,12 +8,10 @@ datasets:
 - tatsu-lab/alpaca
 widget:
 - text: |-
-    ### Instruction:
     Find me a list of some nice places to visit around the world.
     
     ### Response:
 - text: |-
-    ### Instruction:
     Tell me all you know about the Earth.
     
     ### Response:
@@ -35,31 +33,19 @@ inference:
   - GGUF: [afrideva/TinyMistral-248M-Alpaca-GGUF](https://huggingface.co/afrideva/TinyMistral-248M-Alpaca-GGUF)
   - ONNX: [Felladrin/onnx-int8-TinyMistral-248M-Alpaca](https://huggingface.co/Felladrin/onnx-int8-TinyMistral-248M-Alpaca)
 
-## Best Prompt format
-
-The training used these two following formats.
-
-### Prompt format #1
+## Best Prompt Format
 
 ```
-Below is an instruction that describes a task. Write a response that appropriately completes the request.
-
-### Instruction:
 <instruction>
 
 ### Response:
 ```
 
-### Prompt format #2
-
-```
-Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
-
-### Instruction:
-<instruction>
-
-### Input:
-<input>
+## Recommended Parameters
 
-### Response:
-```
+```yml
+repetition_penalty: 1.1
+do_sample: true
+temperature: 0.75
+top_p: 0.5
+```