Hugging Face's logo

Spaces:
kelvin-t-lu
/
chatbot
Paused

App Files Community
chatbot
File size: 2,332 Bytes 
dbd2ac6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
nameOverride: ""
fullnameOverride: h2ogpt

h2ogpt:
  enabled: true
  replicaCount: 1
  image:
    repository: gcr.io/vorvan/h2oai/h2ogpt-runtime
    pullPolicy: IfNotPresent

  storage:
    size: 128Gi
    class: ebs-csi

  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

  service:
    type: NodePort
    webPort: 80
    gptPort: 8888

  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:

  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: ebs-csi
  
  overrideConfig:
  hfSecret: 
  containerArgs:

  service:
    type: ClusterIP
    port: 8080

  updateStrategy:
    type: RollingUpdate

  podSecurityContext:
  securityContext:

  resources:
  nodeSelector:
  tolerations:

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

vllm:
  enabled: false
  replicaCount: 1

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

  imagePullSecrets:

  storage:
    size: 512Gi
    class: ebs-csi
  
  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:

  resources:

  nodeSelector:

  tolerations:

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