sampling-proxy/config_sample.json at master · avtc/sampling-proxy · 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
{
  "server": {
    "target_base_url": "http://127.0.0.1:8000",
    "sampling_proxy_base_path": "",
    "sampling_proxy_host": "0.0.0.0",
    "sampling_proxy_port": 8001,
    "connect_timeout_seconds": 5.0,
    "timeout_seconds": 1200.0,
    "supports_openai": true,
    "supports_anthropic": true
  },
  "logging": {
    "enable_debug_logs": false,
    "enable_override_logs": false,
    "enable_validation_logs": true
  },
  "default_sampling_params": {
    "top_p": null,
    "min_p": null,
    "top_k": null,
    "repetition_penalty": null,
    "temperature": null
  },
  "override": {
    "only_anthropic": false,
    "model_name": null,
    "sampling_params": {
      "top_p": null,
      "min_p": null,
      "top_k": null,
      "repetition_penalty": null,
      "temperature": null
    }
  },
  "model_sampling_params": {
    "sample_model_name": {
        "top_p": null,
        "min_p": null,
        "top_k": null,
        "repetition_penalty": null,
        "temperature": null
    }
  },
  "validation": {
    "enabled": false,
    "mid_stream_validation_enabled": true,
    "mid_stream_validation_interval_words": 300,
    "validator_url": "http://127.0.0.1:1235",
    "validator_model": "Qwen3.5-4B-UD-Q6_K_XL.gguf",
    "supports_openai": true,
    "supports_anthropic": true,
    "connect_timeout_seconds": 5.0,
    "timeout_seconds": 300.0,
    "max_retries": 2,
    "retry_base_delay_seconds": 1.0,
    "retry_multiplier": 2.0,
    "confidence_threshold": 0.85
  },
  "parallel_limits": {
    "global": 999,
    "example-model": 2
  }
}