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.
2024-11-09 16:56:47 +05:30
parent 7c805cfe22
commit fd654cafdb
20 changed files with 119 additions and 17 deletions
--- a/src/assets/locale/fr/common.json
+++ b/src/assets/locale/fr/common.json
@@ -70,6 +70,10 @@
                "label": "Nombre de contextes",
                "placeholder": "Entrez la valeur du nombre de contextes (par défaut: 2048)"
            },
+            "numPredict": {
+                "label": "Tokens maximum (num_predict)",
+                "placeholder": "Entrez la valeur des tokens maximum (par exemple 2048, 4096)"
+            },
            "seed": {
                "label": "Graine",
                "placeholder": "Entrez la valeur des semences (par exemple 1234)",