diff --git a/deploy/llama-factory/Chart.yaml b/deploy/charts/llama-factory/Chart.yaml
similarity index 58%
rename from deploy/llama-factory/Chart.yaml
rename to deploy/charts/llama-factory/Chart.yaml
index ad7ca8025..028244cad 100644
--- a/deploy/llama-factory/Chart.yaml
+++ b/deploy/charts/llama-factory/Chart.yaml
@@ -9,7 +9,11 @@ keywords:
   - llama-factory
   - model tune
 sources:
-  - https://github.com/huangqg/LLaMA-Factory
+  - https://github.com/hiyouga/LLaMA-Factory
 maintainers:
   - name: huangqg
     url: https://github.com/huangqg
+  - name: bjwswang
+    url: https://github.com/bjwswang
+  - name: Lanture1064
+    url: https://github.com/Lanture1064
diff --git a/deploy/charts/llama-factory/README.md b/deploy/charts/llama-factory/README.md
new file mode 100644
index 000000000..557814a5d
--- /dev/null
+++ b/deploy/charts/llama-factory/README.md
@@ -0,0 +1,17 @@
+# llama-factory
+
+Originally from [llama-factory](https://github.com/huangqg/helm-charts/tree/main/charts/llama-factory)
+
+## Usage
+
+Before install llama-factory:
+
+- Must replace `<replaced-ingress-nginx-ip>`with the real ingress ip address(`172.18.0.2` for example) if ingress is enabled
+
+### Install via helm
+
+```shell
+helm install -nkubeagi-system lmf .
+```
+
+If `<replaced-ingress-nginx-ip>` is `172.18.0.2`, then the dashboard of llama factory is `https://lmf.172.18.0.2.nip.io`.
\ No newline at end of file
diff --git a/deploy/charts/llama-factory/templates/deployment.yaml b/deploy/charts/llama-factory/templates/deployment.yaml
new file mode 100644
index 000000000..1695ff744
--- /dev/null
+++ b/deploy/charts/llama-factory/templates/deployment.yaml
@@ -0,0 +1,58 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ .Release.Name }}-llama-factory
+  namespace: {{ .Release.Namespace }}
+  labels:
+    app: {{ .Release.Name }}-llama-factory
+spec:
+  selector:
+    matchLabels:
+      app: {{ .Release.Name }}-llama-factory
+  replicas: 1
+  template:
+    metadata:
+      labels:
+        app: {{ .Release.Name }}-llama-factory
+    spec:
+      containers:
+      - image: {{ .Values.image }}
+        imagePullPolicy: {{ .Values.imagePullPolicy }}
+        name: llama-factory
+        ports:
+        - containerPort: 7860
+          protocol: TCP
+        resources: {{ toYaml .Values.resources | nindent 10 }}
+        volumeMounts:
+          {{- if ne .Values.volume.hf-cache "" }}
+          - name: hf-cache
+            mountPath: /root/.cache/huggingface/
+          {{- end }}
+          {{- if ne .Values.volume.data "" }}
+          - name: data
+            mountPath: /app/data
+          {{- end }}
+          {{- if ne .Values.volume.output "" }}
+          - name: output
+            mountPath: /app/output
+          {{- end }}
+      volumes:
+        {{- if ne .Values.volume.hf-cache "" }}
+        - name: hf-cache
+          hostPath:
+            path: {{ .Values.volume.hf-cache }}
+            type: "Directory"
+        {{- end }}
+        {{- if ne .Values.volume.data "" }}
+        - name: data
+          hostPath:
+            path: {{ .Values.volume.data }}
+            type: "Directory"
+        {{- end }}
+        {{- if ne .Values.volume.output "" }}
+        - name: output
+          hostPath:
+            path: {{ .Values.volume.output }}
+            type: "Directory"
+        {{- end }}
+      terminationGracePeriodSeconds: 30
\ No newline at end of file
diff --git a/deploy/llama-factory/templates/ingress.yaml b/deploy/charts/llama-factory/templates/ingress.yaml
similarity index 90%
rename from deploy/llama-factory/templates/ingress.yaml
rename to deploy/charts/llama-factory/templates/ingress.yaml
index 5df44783b..de73cf0ef 100644
--- a/deploy/llama-factory/templates/ingress.yaml
+++ b/deploy/charts/llama-factory/templates/ingress.yaml
@@ -26,16 +26,16 @@ metadata:
     nginx.ingress.kubernetes.io/upstream-vhost: $host
   labels:
     ingress-lb: {{ .Values.ingress.ingressClassName }}
-  name: llama-factory
+  name: {{ .Release.Name }}-llama-factory
   namespace: {{ .Release.Namespace }}
 spec:
   rules:
-    - host: portal.{{ .Values.ingress.ingressDomain }}
+    - host: {{ .Release.Name }}.{{ .Values.ingress.ingressDomain }}
       http:
         paths:
           - backend:
               service:
-                name: llama-factory
+                name: {{ .Release.Name }}-llama-factory
                 port:
                   number: 7860
             path: /
diff --git a/deploy/charts/llama-factory/templates/menus.yaml b/deploy/charts/llama-factory/templates/menus.yaml
new file mode 100644
index 000000000..7eb7797e1
--- /dev/null
+++ b/deploy/charts/llama-factory/templates/menus.yaml
@@ -0,0 +1,52 @@
+{{ if .Capabilities.APIVersions.Has "core.kubebb.k8s.com.cn/v1alpha1/Menu" -}}
+apiVersion: core.kubebb.k8s.com.cn/v1alpha1
+kind: Menu
+metadata:
+  name: kubeagi-model-tune
+spec:
+  disabled: false
+  rankingInColumn: 400
+  target: ""
+  text: 模型调优
+  textEn: model_tuneing
+  parentOwnerReferences:
+    apiVersion: core.kubebb.k8s.com.cn/v1alpha1
+    kind: Menu
+    name: yunti-kubeagi-portal
+    uid: ""
+---
+apiVersion: core.kubebb.k8s.com.cn/v1alpha1
+kind: Menu
+metadata:
+  name: kubeagi-model-tune-submenu
+spec:
+  parentOwnerReferences:
+    apiVersion: core.kubebb.k8s.com.cn/v1alpha1
+    kind: Menu
+    name: kubeagi-model-tune
+    uid: ""
+  cluster: false
+  disabled: false
+  icon: '{"name":"Ai","data":"<path d=\"M334.351 1023.768c-46.718 0-84.33-12.976-111.596-40.217-84.33-75.25-59.694-230.958-59.694-236.143l-5.185-5.185-108.991-32.427c-12.976-5.185-27.242-12.976-32.427-27.241-5.185-14.266-5.185-29.847
+    2.606-42.823 0 0 62.273-119.361 121.967-238.748C143.636 206.348 244.836.052 525.09.052c168.685
+    0 272.491 67.458 326.974 124.572 59.694 62.273 79.144 124.572 79.144 127.152 2.606
+    5.185 64.879 184.24-35.032 349.03-81.75 138.837-35.032 219.271-32.426 224.482
+    7.79 12.976 2.605 29.847-7.79 37.637-12.976 7.791-29.847 5.186-37.638-7.79-2.606-5.185-71.354-111.597
+    29.847-281.571 84.33-144.023 29.846-303.627 29.846-306.207-2.605-10.37-67.458-211.507-354.214-211.507-304.917
+    0-329.579 271.175-329.579 355.53v5.185l-2.605 5.185C137.109 530.741 80.02 635.837
+    69.65 660.5l103.806 29.846c27.241 7.791 46.718 35.032 44.112 62.274 0 2.605-19.45
+    134.942 40.217 189.425 29.847 27.241 79.145 32.426 141.418 16.87 40.217-10.37
+    79.144-29.846 111.596-42.822 37.638-19.45 71.354-32.426 101.2-32.426 51.904 0
+    81.75 51.903 92.12 81.75 5.186 12.975-2.605 29.846-19.45 35.032-12.976 5.185-29.847-2.606-35.032-19.451-2.605-10.37-19.45-42.823-37.637-42.823-16.871
+    0-46.718 12.976-76.565 27.242-35.032 16.87-76.564 35.032-121.966 49.297-27.216
+    5.16-51.878 9.055-79.119 9.055zm89.902-783.42H397.01l-163.5 433.359h54.51l40.216-108.991h190.741l40.217
+    108.99h54.508L450.204 240.349h-25.951zm-84.356 281.57l84.33-224.482 92.12 224.483h-176.45zm356.82-281.57h54.509v433.359h-54.509z\"></path>"}'
+  pathname: /oidc/tune-model
+  project: false
+  rankingInColumn: 96
+  redirect: https://{{ .Release.Name }}.{{ .Values.ingress.ingressDomain }}
+  target: iframe
+  tenant: false
+  text: 模型调优
+  textEn: model_tuning
+{{- end }}
diff --git a/deploy/llama-factory/templates/service.yaml b/deploy/charts/llama-factory/templates/service.yaml
similarity index 64%
rename from deploy/llama-factory/templates/service.yaml
rename to deploy/charts/llama-factory/templates/service.yaml
index 57a772076..4d0f320e1 100644
--- a/deploy/llama-factory/templates/service.yaml
+++ b/deploy/charts/llama-factory/templates/service.yaml
@@ -2,8 +2,8 @@ apiVersion: v1
 kind: Service
 metadata:
   labels:
-    app: llama-factory
-  name: llama-factory
+    app: {{ .Release.Name }}-llama-factory
+  name: {{ .Release.Name }}-llama-factory
   namespace: {{ .Release.Namespace }}
 spec:
   ports:
@@ -12,6 +12,6 @@ spec:
       protocol: TCP
       targetPort: 7860
   selector:
-    app: llama-factory
+    app: {{ .Release.Name }}-llama-factory
   sessionAffinity: None
   type: ClusterIP
diff --git a/deploy/charts/llama-factory/values.yaml b/deploy/charts/llama-factory/values.yaml
new file mode 100644
index 000000000..90002c3fd
--- /dev/null
+++ b/deploy/charts/llama-factory/values.yaml
@@ -0,0 +1,29 @@
+# ingress configurations for component
+ingress:
+  # set enable to `true` to enable ingress
+  enable: true
+  ingressClassName: portal-ingress
+  ingressDomain: <replaced-ingress-nginx-ip>.nip.io
+
+# volume configurations for llama-factory
+volume:
+  # hf-cache is the cache path for huggingface model from host 
+  hf-cache: ""
+  # data is the data path for llama-factory from host
+  data: ""
+  # output is the output path for llama-factory from host
+  output: ""
+
+# llama-factory configurations
+image: kubeagi/llama-factory:v0.6.1
+imagePullPolicy: IfNotPresent
+resources:
+  limits:
+    cpu: "4"
+    memory: 12Gi
+    nvidia.com/gpu: "0"
+  requests:
+    cpu: "1"
+    memory: 1Gi
+    nvidia.com/gpu: "0"
+
diff --git a/deploy/llama-factory/README.md b/deploy/llama-factory/README.md
deleted file mode 100644
index 9725b7620..000000000
--- a/deploy/llama-factory/README.md
+++ /dev/null
@@ -1 +0,0 @@
-# llama-factory
\ No newline at end of file
diff --git a/deploy/llama-factory/templates/deployment.yaml b/deploy/llama-factory/templates/deployment.yaml
deleted file mode 100644
index bff568e43..000000000
--- a/deploy/llama-factory/templates/deployment.yaml
+++ /dev/null
@@ -1,43 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: llama-factory
-  namespace: {{ .Release.Namespace }}
-  labels:
-    app: llama-factory
-spec:
-  selector:
-    matchLabels:
-      app: llama-factory
-  replicas: 1
-  template:
-    metadata:
-      labels:
-        app: llama-factory
-    spec:
-      containers:
-      - image: {{ .Values.image }}
-        imagePullPolicy: {{ .Values.imagePullPolicy }}
-        name: llama-factory
-        ports:
-        - containerPort: 7860
-          protocol: TCP
-        resources: {{ toYaml .Values.resources | nindent 10 }}
-        volumeMounts:
-          - name: model-volume
-            mountPath: /root/.cache/huggingface
-          - name: data-volume
-            mountPath: /app/data
-          - name: output-volume
-            mountPath: /app/output
-      volumes:
-        - name: model-volume
-          hostPath:
-            path: {{ .Values.volume.model }}
-        - name: data-volume
-          hostPath:
-            path: {{ .Values.volume.data }}
-        - name: output-volume
-          hostPath:
-            path: {{ .Values.volume.output }}
-      terminationGracePeriodSeconds: 30
\ No newline at end of file
diff --git a/deploy/llama-factory/values.yaml b/deploy/llama-factory/values.yaml
deleted file mode 100644
index d8366e257..000000000
--- a/deploy/llama-factory/values.yaml
+++ /dev/null
@@ -1,23 +0,0 @@
-image: kubeagi/llama-factory:v0.6.1
-imagePullPolicy: IfNotPresent
-resources:
-  limits:
-    cpu: "4"
-    memory: 12Gi
-    nvidia.com/gpu: "1"
-  requests:
-    cpu: "1"
-    memory: 1Gi
-    nvidia.com/gpu: "1"
-
-volume:
-  model: /path/to/model/or/cache
-  data: /path/to/data
-  output: /path/to/output
-
-# ingress configurations for component
-ingress:
-  # set enable to `true` to enable ingress
-  enable: true
-  ingressClassName: portal-ingress
-  ingressDomain: your.domain.nip.io