qbitos-freya/BACKEND_MATRIX.json at main · qbitOS/qbitos-freya · GitHub

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
{
  "version": "1.0.0",
  "defaultBackend": "auto",
  "autoFallbackOrder": [
    "lmstudio",
    "ollama",
    "ugrad",
    "huggingface",
    "mistral"
  ],
  "backends": {
    "lmstudio": {
      "protocol": "openai_compatible",
      "baseUrlEnv": "LOCAL_LLM_BASE_URL",
      "modelEnv": "LOCAL_LLM_MODEL",
      "apiKeyEnv": "LOCAL_LLM_API_KEY",
      "defaultBaseUrl": "http://127.0.0.1:1234/v1",
      "notes": "Use for local LM Studio model serving."
    },
    "ollama": {
      "protocol": "ollama_api",
      "baseUrlEnv": "OLLAMA_BASE_URL",
      "modelEnv": "OLLAMA_MODEL",
      "defaultBaseUrl": "http://127.0.0.1:11434",
      "notes": "Use for local Ollama models."
    },
    "ugrad": {
      "protocol": "openai_compatible",
      "baseUrlEnv": "UGRAD_MODELLAB_BASE_URL",
      "modelEnv": "UGRAD_MODELLAB_MODEL",
      "apiKeyEnv": "UGRAD_MODELLAB_API_KEY",
      "notes": "Use for ugrad Model Lab gateway."
    },
    "huggingface": {
      "protocol": "hf_inference_api",
      "tokenEnv": "HF_API_TOKEN",
      "modelEnv": "HF_MODEL",
      "notes": "Hosted inference via Hugging Face API."
    },
    "mistral": {
      "protocol": "mistral_sdk",
      "apiKeyEnv": "MISTRAL_API_KEY",
      "modelEnv": "MISTRAL_MODEL",
      "notes": "Hosted inference via Mistral SDK."
    }
  },
  "modelFamilyAliases": {
    "llama2": {
      "ollama": "llama2",
      "huggingface": "meta-llama/Llama-2-7b-chat-hf",
      "lmstudio": "llama-2",
      "ugrad": "llama-2"
    },
    "llama3": {
      "ollama": "llama3.1",
      "huggingface": "meta-llama/Llama-3.1-8B-Instruct",
      "lmstudio": "llama-3",
      "ugrad": "llama-3"
    },
    "mistral": {
      "ollama": "mistral",
      "huggingface": "mistralai/Mistral-7B-Instruct-v0.3",
      "lmstudio": "mistral",
      "ugrad": "mistral",
      "mistral": "mistral-small-latest"
    },
    "falcon": {
      "ollama": "falcon",
      "huggingface": "tiiuae/falcon-7b-instruct",
      "lmstudio": "falcon",
      "ugrad": "falcon"
    },
    "gptneo": {
      "ollama": "gpt-neo",
      "huggingface": "EleutherAI/gpt-neo-2.7B",
      "lmstudio": "gpt-neo",
      "ugrad": "gpt-neo"
    },
    "codellama": {
      "ollama": "codellama",
      "huggingface": "meta-llama/CodeLlama-7b-Instruct-hf",
      "lmstudio": "codellama",
      "ugrad": "codellama"
    },
    "vicuna": {
      "ollama": "vicuna",
      "huggingface": "lmsys/vicuna-7b-v1.5",
      "lmstudio": "vicuna",
      "ugrad": "vicuna"
    }
  },
  "security": {
    "neverCommitSecrets": true,
    "requiredSecretEnvVars": [
      "MISTRAL_API_KEY",
      "HF_API_TOKEN",
      "UGRAD_MODELLAB_API_KEY",
      "LOCAL_LLM_API_KEY"
    ]
  }
}