Hugging Face's logo

Spaces:
iblfe
/
test
Runtime error

App Files Community
test
File size: 2,846 Bytes 
b585c7f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
 
nameOverride: ""
fullnameOverride: ""

h2ogpt:
  enabled: true
  stack:
    # -- Run h2oGPT and vLLM on same pod.
    enabled: false 
  replicaCount: 1
  image:
    repository: gcr.io/vorvan/h2oai/h2ogpt-runtime
    pullPolicy: IfNotPresent
  initImage:
    repository:
    tag:
    pullPolicy:

  storage:
    size: 128Gi
    class: 
    useEphemeral: true
  
  externalLLM:
    enabled: false
    secret:

    modelLock:

    openAIAzure:
      enabled: false

    openAI:
      enabled: False

    replicate: 
      enabled: false

# -- Example configs to use when not using Model Lock and External LLM
  # overrideConfig:
  #   base_model: h2oai/h2ogpt-4096-llama2-7b-chat
  #   use_safetensors: True
  #   prompt_type: llama2
  #   save_dir: /workspace/save/
  #   use_gpu_id: False
  #   score_model: None
  #   max_max_new_tokens: 2048
  #   max_new_tokens: 1024

  overrideConfig:


  service:
    type: NodePort
    webPort: 80
    gptPort: 8888
    webServiceAnnotations: {}

  updateStrategy:
    type: RollingUpdate

  podSecurityContext:
    runAsNonRoot: true
    runAsUser: 1000
    runAsGroup: 1000
    fsGroup: 1000

  securityContext:
    runAsNonRoot: true
    allowPrivilegeEscalation: false
    capabilities:
      drop:
        - ALL
    seccompProfile:
      type: RuntimeDefault

  resources:
  nodeSelector:
  tolerations:

  env: {}

  podAnnotations: {}
  podLabels: {}
  autoscaling: {}

tgi:
  enabled: false
  replicaCount: 1

  image:
    repository: ghcr.io/huggingface/text-generation-inference
    tag: 0.9.3
    pullPolicy: IfNotPresent

  storage:
    size: 512Gi
    class: 
    useEphemeral: true
  
  overrideConfig:
  hfSecret:
  containerArgs:

  service:
    type: ClusterIP
    port: 8080

  updateStrategy:
    type: RollingUpdate

  podSecurityContext:
  securityContext:

  resources:
  nodeSelector:
  tolerations:

  env: {}

  podAnnotations: {}
  podLabels: {}
  autoscaling: {}

vllm:
  enabled: false
  replicaCount: 1

  image:
    repository: gcr.io/vorvan/h2oai/h2ogpt-runtime
    pullPolicy: IfNotPresent

  imagePullSecrets:

  storage:
    size: 512Gi
    class: 
    useEphemeral: true
  
  overrideConfig:

  containerArgs:
    - "--model"
    - h2oai/h2ogpt-4096-llama2-7b-chat
    - "--tokenizer"
    - hf-internal-testing/llama-tokenizer
    - "--tensor-parallel-size"
    - 2
    - "--seed"
    - 1234
    - "--trust-remote-code"

  service:
    type: ClusterIP
    port: 5000

  updateStrategy:
    type: RollingUpdate

  podSecurityContext:
    runAsNonRoot: true
    runAsUser: 1000
    runAsGroup: 1000
    fsGroup: 1000

  securityContext:
    runAsNonRoot: true
    allowPrivilegeEscalation: false
    capabilities:
      drop:
        - ALL
    seccompProfile:

  env: {}

  resources:

  nodeSelector:

  tolerations:

  podAnnotations: {}
  podLabels: {}
  autoscaling: {}