Update README.md

README.md

@@ -45,15 +45,15 @@ For fast inference use, we would recommend the 'quantized tool' version, e.g.,
         eos_token_id=tokenizer.eos_token_id,
         pad_token_id=tokenizer.eos_token_id,
         do_sample=True,
-        temperature=0.3,
-        max_new_tokens=100
+        temperature=0.7,
+        max_new_tokens=200
     )
 
     output_only = tokenizer.decode(outputs[0][start_of_input:], skip_special_tokens=True)
 
     print("output only: ", output_only)  
 
-    `{'llm_response': {'question': ['Did Telsa stock decline more than 8% yesterday?']} }`  
+    [OUTPUT]:  {'llm_response': {'question': ['Did Telsa stock decline more than 8% yesterday?']} }  
     
     # here's the fun part
     try:
@@ -72,10 +72,10 @@ For fast inference use, we would recommend the 'quantized tool' version, e.g.,
 <summary>Using as Function Call in LLMWare</summary>
 
     from llmware.models import ModelCatalog
-    slim_model = ModelCatalog().load_model("llmware/slim-q-gen-phi-3")
-    response = slim_model.function_call(text,params=["boolean"], function="generate")
+    slim_model = ModelCatalog().load_model("llmware/slim-q-gen-phi-3", sample=True, temperature=0.7)  
+    response = slim_model.function_call(text,params=["boolean"], function="generate")  
 
-    print("llmware - llm_response: ", response)
+    print("llmware - llm_response: ", response)  
 
 </details>