feat: Add max tokens setting for model generations

Adds a new setting to control the maximum number of tokens generated by the model. This provides more control over the length of responses and can be useful for limiting the amount of text generated in certain situations.

src/assets/locale/en/common.json

@@ -70,6 +70,10 @@
                 "label": "Number of Contexts",
                 "placeholder": "Enter Number of Contexts value (default: 2048)"
             },
+            "numPredict": {
+                "label": "Max Tokens (num_predict)",
+                "placeholder": "Enter Max Tokens value (e.g. 2048, 4096)"
+            },
             "seed": {
                 "label": "Seed",
                 "placeholder": "Enter Seed value (e.g. 1234)",