added options to set temperature, top_p, frequency_penelty, presence_penalty

installer/client/cli/fabric.py

@@ -39,6 +39,14 @@ def main():
     parser.add_argument(
         "--list", "-l", help="List available patterns", action="store_true"
     )
+    parser.add_argument(
+        '--temp', help="set the temperature for the model. Default is 0", default=0, type=float)
+    parser.add_argument(
+        '--top_p', help="set the top_p for the model. Default is 1", default=1, type=float)
+    parser.add_argument(
+        '--frequency_penalty', help="set the frequency penalty for the model. Default is 0.1", default=0.1, type=float)
+    parser.add_argument(
+        '--presence_penalty', help="set the presence penalty for the model. Default is 0.1", default=0.1, type=float)
     parser.add_argument(
         "--update", "-u", help="Update patterns. NOTE: This will revert the default model to gpt4-turbo. please run --changeDefaultModel to once again set default model", action="store_true")
     parser.add_argument("--pattern", "-p", help="The pattern (prompt) to use")

installer/client/cli/utils.py

@@ -87,7 +87,7 @@ class Standalone:
             max_tokens=4096,
             system=system,
             messages=[user],
-            model=self.model, temperature=0.0, top_p=1.0
+            model=self.model, temperature=self.args.temp, top_p=self.args.top_p
         ) as stream:
             async for text in stream.text_stream:
                 print(text, end="", flush=True)
@@ -104,7 +104,7 @@ class Standalone:
             system=system,
             messages=[user],
             model=self.model,
-            temperature=0.0, top_p=1.0
+            temperature=self.args.temp, top_p=self.args.top_p
         )
         print(message.content[0].text)
         copy = self.args.copy
@@ -162,10 +162,10 @@ class Standalone:
                 stream = self.client.chat.completions.create(
                     model=self.model,
                     messages=messages,
-                    temperature=0.0,
-                    top_p=1,
-                    frequency_penalty=0.1,
-                    presence_penalty=0.1,
+                    temperature=self.args.temp,
+                    top_p=self.args.top_p,
+                    frequency_penalty=self.args.frequency_penalty,
+                    presence_penalty=self.args.presence_penalty,
                     stream=True,
                 )
                 for chunk in stream:
@@ -247,10 +247,10 @@ class Standalone:
                 response = self.client.chat.completions.create(
                     model=self.model,
                     messages=messages,
-                    temperature=0.0,
-                    top_p=1,
-                    frequency_penalty=0.1,
-                    presence_penalty=0.1,
+                    temperature=self.args.temp,
+                    top_p=self.args.top_p,
+                    frequency_penalty=self.args.frequency_penalty,
+                    presence_penalty=self.args.presence_penalty,
                 )
                 print(response.choices[0].message.content)
                 if self.args.copy: