Repository navigation
Expand file tree
/
Copy pathmodels.yaml
More file actions
65 lines (65 loc) · 1.51 KB
/
Copy pathmodels.yaml
File metadata and controls
65 lines (65 loc) · 1.51 KB
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
models:
generalist-slm:
provider: mock
endpoint: mock://generalist
tags: [general, qa, reasoning]
max_context_tokens: 2048
latency_ms: 150
cost_per_1k_tokens: 0.001
weight: 0.65
code-slm:
provider: mock
endpoint: mock://code
tags: [coding, technical]
max_context_tokens: 4096
latency_ms: 180
cost_per_1k_tokens: 0.002
weight: 0.85
reasoning-slm:
provider: mock
endpoint: mock://reasoning
tags: [reasoning, technical, general]
max_context_tokens: 4096
latency_ms: 210
cost_per_1k_tokens: 0.002
weight: 0.8
math-slm:
provider: mock
endpoint: mock://math
tags: [math, reasoning]
max_context_tokens: 2048
latency_ms: 140
cost_per_1k_tokens: 0.001
weight: 0.8
finance-slm:
provider: mock
endpoint: mock://finance
tags: [finance, qa, summarization]
max_context_tokens: 4096
latency_ms: 190
cost_per_1k_tokens: 0.002
weight: 0.82
summary-slm:
provider: mock
endpoint: mock://summary
tags: [summarization, general]
max_context_tokens: 4096
latency_ms: 160
cost_per_1k_tokens: 0.0015
weight: 0.75
medical-qa-slm:
provider: mock
endpoint: mock://medical
tags: [medical, qa]
max_context_tokens: 4096
latency_ms: 220
cost_per_1k_tokens: 0.0025
weight: 0.86
creative-slm:
provider: mock
endpoint: mock://creative
tags: [creative, writing]
max_context_tokens: 2048
latency_ms: 170
cost_per_1k_tokens: 0.001
weight: 0.7