handle partially quantized models (#76)

* handle partially quantized models

- fix for #53 #71 #69 #74
- in order to test the models
	- I added a default prompt of an appropriate form
	- while working on the model configuration also added additional stop tokens (#74)
- fixed the repetitionPenalty code (#71)

Tools/llm-tool/LoraCommands.swift

@@ -275,7 +275,8 @@ struct LoRAEvalCommand: AsyncParsableCommand {
 
         // generate and print the result
         let _ = await generate.generate(
-            promptTokens: promptTokens, model: model, tokenizer: tokenizer)
+            promptTokens: promptTokens, model: model, tokenizer: tokenizer,
+            extraEOSTokens: modelConfiguration.extraEOSTokens)
         print()
     }
 }