File size: 2,091 Bytes
3fdf87c
 
0c0f086
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7200b01
 
0c0f086
 
 
 
 
 
 
 
7200b01
efaad9e
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
"""Module containing model configuration results for various AI models and hardware setups."""

from results_arcee_agent import results_arcee_agent
from results_arcee_lite import results_arcee_lite
from results_arcee_meraj import results_arcee_meraj
from results_arcee_nova import results_arcee_nova
from results_arcee_scribe import results_arcee_scribe
from results_arcee_spark import results_arcee_spark
from results_arcee_supernova import results_arcee_supernova
from results_llama_spark import results_llama_spark

instance_type_mappings = {
    "g5.xlarge": {"cloud": "AWS", "gpu": "1xNVIDIA A10G", "gpuRAM": "24 GB"},
    "g5.2xlarge": {"cloud": "AWS", "gpu": "1xNVIDIA A10G", "gpuRAM": "24 GB"},
    "g5.12xlarge": {"cloud": "AWS", "gpu": "4xNVIDIA A10G", "gpuRAM": "96 GB"},
    "g5.48xlarge": {"cloud": "AWS", "gpu": "8xNVIDIA A10G", "gpuRAM": "192 GB"},
    "g6.2xlarge": {"cloud": "AWS", "gpu": "1xNVIDIA L4", "gpuRAM": "24 GB"},
    "g6.12xlarge": {"cloud": "AWS", "gpu": "4xNVIDIA L4", "gpuRAM": "96 GB"},
    "g6.48xlarge": {"cloud": "AWS", "gpu": "8xNVIDIA L4", "gpuRAM": "192 GB"},
    "g6e.2xlarge": {"cloud": "AWS", "gpu": "1xNVIDIA L40S", "gpuRAM": "48 GB"},
    "g4dn.12xlarge": {"cloud": "AWS", "gpu": "4xNVIDIA T4", "gpuRAM": "64 GB"},
    "p4d.24xlarge": {"cloud": "AWS", "gpu": "4xNVIDIA A100", "gpuRAM": "320 GB"},
    "p4de.24xlarge": {"cloud": "AWS", "gpu": "8xNVIDIA A100", "gpuRAM": "320 GB"},
    "p5.48xlarge": {"cloud": "AWS", "gpu": "8xNVIDIA H100", "gpuRAM": "640GB"},
    "c6i.xlarge": {"cloud": "AWS", "gpu": "-", "gpuRAM": "-"},
    "c6i.2xlarge": {"cloud": "AWS", "gpu": "-", "gpuRAM": "-"},
    "c6i.4xlarge": {"cloud": "AWS", "gpu": "-", "gpuRAM": "-"},
    "c7i.4xlarge": {"cloud": "AWS", "gpu": "-", "gpuRAM": "-"},
    "inf2.*": {"cloud": "AWS", "gpu": "-", "gpuRAM": "-"},
}

results = {
    "models": [
        results_arcee_meraj,
        results_arcee_supernova,
        results_arcee_nova,
        results_llama_spark,
        results_arcee_agent,
        results_arcee_spark,
        results_arcee_lite,
        results_arcee_scribe,
    ]
}