Changed default model to DeepSeek

charts/azimuth-chat/values.schema.json

@@ -11,7 +11,7 @@
                             "type": "string",
                             "title": "Model",
                             "description": "The [HuggingFace model](https://huggingface.co/models) to deploy (see [here](https://github.com/stackhpc/azimuth-llm?tab=readme-ov-file#tested-models) for a list of tested models).",
-                            "default": "microsoft/Phi-3.5-mini-instruct"
+                            "default": "deepseek-ai/deepseek-llm-7b-chat"
                         },
                         "token": {
                             "type": [

charts/azimuth-chat/values.yaml

@@ -1,6 +1,6 @@
 azimuth-llm:
   huggingface:
-    model: &model-name microsoft/Phi-3.5-mini-instruct
+    model: &model-name deepseek-ai/deepseek-llm-7b-chat
   ui:
     image:
       repository: ghcr.io/stackhpc/azimuth-llm-chat-ui

charts/azimuth-llm/values.schema.json

@@ -8,7 +8,7 @@
                     "type": "string",
                     "title": "Model",
                     "description": "The [HuggingFace model](https://huggingface.co/models) to deploy (see [here](https://github.com/stackhpc/azimuth-llm?tab=readme-ov-file#tested-models) for a list of tested models).",
-                    "default": "microsoft/Phi-3.5-mini-instruct"
+                    "default": "deepseek-ai/deepseek-llm-7b-chat"
                 },
                 "token": {
                     "type": [

charts/azimuth-llm/values.yaml

@@ -5,7 +5,7 @@
 huggingface:
   # The name of the HuggingFace model to use
   # Use a yaml anchor to avoid duplication elsewhere
-  model: &model-name microsoft/Phi-3.5-mini-instruct
+  model: &model-name deepseek-ai/deepseek-llm-7b-chat
   # A Jinja formatted chat template to provide to the language model.
   # See https://huggingface.co/blog/chat-templates for background info.
   # If not provided, the default template specified in the HuggingFace