DMind-Benchmark/models.yml at main · DMindAI/DMind-Benchmark · 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
# API Base URL Configuration
# ===============================
# Main API Base URL (Currently Active)
api_base: "xxx"
# Alternative API Base URLs (Switch by commenting/uncommenting)
# api_base: "xxx"

# Third-party Evaluation API Configuration
# ===============================
# Evaluation API Base URL (Optional, uses the above api_base if not set)
evaluation_api_base: "xxx"
# Alternative Evaluation API Base URLs


# API Key Configuration
# ===============================
api_keys:
  # Existing API Keys
  - key: "xxx"
    name: "xxx"


  # Evaluation API Keys
  - key: "xxx"
    name: "claude_eval"
    model_name: "claude-3-7-sonnet-20250219"
  - key: "xxx"
    name: "openai_eval"
    model_name: "gpt-4o"

# Model Configuration
# ===============================
models:
  # Commented Model Configurations (Original Configurations Preserved)
  # - name: "claude-3-5-haiku-20241022"
  #   provider: "anthropic"
  #   model: "claude-3-5-haiku-20241022"
  #   parameters:
  #     temperature: 0.7
  #     max_tokens: 1000
  #   api_key: "xxxx"

  # ... [Other commented model configurations] ...

  # Existing Model Configurations
  - name: "xxx"
    provider: "xxx"
    model: "xxx"
    api_key: "xxx"

  # Evaluation Model Configurations
  - name: "claude_evaluation"
    provider: "anthropic"
    model: "claude-3-7-sonnet-20250219"
    parameters:
      temperature: 0
      max_tokens: 4000
    api_key: "claude_eval"
    api_base: "xxx"

  - name: "gpt4_evaluation"
    provider: "openai"
    model: "gpt-4o"
    parameters:
      temperature: 0
      max_tokens: 4000
    api_key: "openai_eval"
    api_base: "xxx"