-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathvalues.schema.json
131 lines (131 loc) · 6.99 KB
/
values.schema.json
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
{
"type": "object",
"properties": {
"azimuth-llm": {
"type": "object",
"properties": {
"huggingface": {
"type": "object",
"properties": {
"model": {
"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": "Qwen/Qwen2-VL-7B-Instruct"
},
"token": {
"type": [
"string",
"null"
],
"title": "Access Token",
"description": "A HuggingFace [access token](https://huggingface.co/docs/hub/security-tokens). Required for [gated models](https://huggingface.co/docs/hub/en/models-gated) (e.g. Llama 3)."
}
},
"required": [
"model"
]
},
"api": {
"type": "object",
"properties": {
"image": {
"type": "object",
"properties": {
"version": {
"type": "string",
"title": "Backend vLLM version",
"description": "The vLLM version to use as a backend. Must be a version tag from [this list](https://github.com/vllm-project/vllm/tags)",
"default": "v0.7.2"
}
}
},
"modelMaxContextLength": {
"title": "Model Context Length",
"description": "An override for the maximum context length to allow, if the model's default is not suitable."
}
}
},
"ui": {
"type": "object",
"properties": {
"appSettings": {
"type": "object",
"properties": {
"model_name": {
"type": "string",
"title": "Model Name",
"description": "Model name supplied to the OpenAI client in frontend web app. Should match huggingface.model above."
},
"page_title": {
"type": "string",
"title": "Page Title",
"description": "The title to display at the top of the chat interface.",
"default": "Vision Model Image Analysis"
},
"llm_params": {
"$comment": "top_k parameter causes vLLM to error for most (all?) vision models so is excluded here",
"type": "object",
"properties": {
"max_tokens": {
"type": "integer",
"title": "Max Tokens",
"description": "The maximum number of new [tokens](https://platform.openai.com/docs/api-reference/chat/create#chat-create-max_tokens) to generate for each LLM responses.",
"default": 1000
},
"temperature": {
"type": "number",
"title": "LLM Temperature",
"description": "The [temperature](https://platform.openai.com/docs/api-reference/chat/create#chat-create-temperature) value to use when generating LLM responses.",
"default": 0,
"minimum": 0,
"maximum": 2
},
"top_p": {
"type": "number",
"title": "LLM Top P",
"description": "The [top p](https://platform.openai.com/docs/api-reference/chat/create#chat-create-top_p) value to use when generating LLM responses.",
"default": 1,
"exclusiveMinimum": 0,
"maximum": 1
},
"presence_penalty": {
"type": "number",
"title": "LLM Presence Penalty",
"description": "The [presence penalty](https://platform.openai.com/docs/api-reference/chat/create#chat-create-presence_penalty) to use when generating LLM responses.",
"default": 0,
"minimum": -2,
"maximum": 2
},
"frequency_penalty": {
"type": "number",
"title": "LLM Frequency Penalty",
"description": "The [frequency_penalty](https://platform.openai.com/docs/api-reference/chat/create#chat-create-frequency_penalty) to use when generating LLM responses.",
"default": 0,
"minimum": -2,
"maximum": 2
}
}
}
},
"required": [
"model_name"
]
}
}
}
}
},
"api": {
"properties": {
"image": {
"properties": {
"version": {
"default": "v0.7.3"
}
}
}
}
}
}
}