Pass TRUNCATE_PROMPT_LENGTH to deployment, switch to ghcr.io image (

#63) Signed-off-by: Hung-Han (Henry) Chen <chenhungh@gmail.com>
chenhunghan · Aug 26, 2023 · 4f651e3 · 4f651e3
1 parent 2f03dee
commit 4f651e3
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 3 deletions.
diff --git a/charts/ialacol/Chart.yaml b/charts/ialacol/Chart.yaml
@@ -1,6 +1,6 @@
 apiVersion: v2
-appVersion: 0.11.0
+appVersion: 0.11.1
 description: A Helm chart for ialacol
 name: ialacol
 type: application
-version: 0.11.0
+version: 0.11.1
diff --git a/charts/ialacol/templates/deployment.yaml b/charts/ialacol/templates/deployment.yaml
@@ -57,6 +57,8 @@ spec:
             value: {{ (.Values.deployment.env).GPU_LAYERS | quote }}
           - name: MODE_TYPE
             value: {{ (.Values.deployment.env).MODE_TYPE | quote }}
+          - name: TRUNCATE_PROMPT_LENGTH
+            value: {{ (.Values.deployment.env).TRUNCATE_PROMPT_LENGTH | quote }}
           volumeMounts:
           - mountPath: /app/models
             name: model

diff --git a/charts/ialacol/values.yaml b/charts/ialacol/values.yaml
@@ -1,7 +1,7 @@
 replicas: 1
 
 deployment:
-  image: quay.io/chenhunghan/ialacol:latest
+  image: ghcr.io/chenhunghan/ialacol:latest
   # or use CUDA image `ghcr.io/chenhunghan/ialacol-cuda12:latest`
   # env:
     # DEFAULT_MODEL_HG_REPO_ID: TheBloke/Llama-2-7B-Chat-GGML