File size: 3,237 Bytes
256a159
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from mmengine.config import read_base
from opencompass.models.turbomind import TurboMindModel

with read_base():
    # choose a list of datasets
    from .datasets.mmlu.mmlu_gen_a484b3 import mmlu_datasets
    from .datasets.ceval.ceval_gen_5f30c7 import ceval_datasets
    from .datasets.SuperGLUE_WiC.SuperGLUE_WiC_gen_d06864 import WiC_datasets
    from .datasets.SuperGLUE_WSC.SuperGLUE_WSC_gen_7902a7 import WSC_datasets
    from .datasets.triviaqa.triviaqa_gen_2121ce import triviaqa_datasets
    from .datasets.gsm8k.gsm8k_gen_1d7fe4 import gsm8k_datasets
    from .datasets.race.race_gen_69ee4f import race_datasets
    from .datasets.crowspairs.crowspairs_gen_381af0 import crowspairs_datasets
    # and output the results in a choosen format
    from .summarizers.medium import summarizer


datasets = sum((v for k, v in locals().items() if k.endswith('_datasets')), [])

internlm_meta_template = dict(round=[
    dict(role='HUMAN', begin='<|User|>:', end='\n'),
    dict(role='BOT', begin='<|Bot|>:', end='<eoa>\n', generate=True),
],
                              eos_token_id=103028)

internlm2_meta_template = dict(
    round=[
        dict(role='HUMAN', begin='<|im_start|>user\n', end='<|im_end|>\n'),
        dict(role='BOT', begin='<|im_start|>assistant\n', end='<|im_end|>\n', generate=True),
    ],
    eos_token_id=92542
)

# config for internlm-chat-7b
internlm_chat_7b = dict(
    type=TurboMindModel,
    abbr='internlm-chat-7b-turbomind',
    path='internlm/internlm-chat-7b',
    engine_config=dict(session_len=2048,
                       max_batch_size=32,
                       rope_scaling_factor=1.0),
    gen_config=dict(top_k=1,
                    top_p=0.8,
                    temperature=1.0,
                    max_new_tokens=100),
    max_out_len=100,
    max_seq_len=2048,
    batch_size=32,
    concurrency=32,
    meta_template=internlm_meta_template,
    run_cfg=dict(num_gpus=1, num_procs=1),
    end_str='<eoa>',
)

# config for internlm-chat-7b
internlm2_chat_7b = dict(
    type=TurboMindModel,
    abbr='internlm2-chat-7b-turbomind',
    path='internlm/internlm2-chat-7b',
    engine_config=dict(session_len=2048,
                       max_batch_size=32,
                       rope_scaling_factor=1.0),
    gen_config=dict(top_k=1,
                    top_p=0.8,
                    temperature=1.0,
                    max_new_tokens=100),
    max_out_len=100,
    max_seq_len=2048,
    batch_size=32,
    concurrency=32,
    meta_template=internlm2_meta_template,
    run_cfg=dict(num_gpus=1, num_procs=1),
    end_str='<|im_end|>'
)

# config for internlm-chat-20b
internlm_chat_20b = dict(
    type=TurboMindModel,
    abbr='internlm-chat-20b-turbomind',
    path='internlm/internlm-chat-20b',
    engine_config=dict(session_len=2048,
                       max_batch_size=8,
                       rope_scaling_factor=1.0),
    gen_config=dict(top_k=1,
                    top_p=0.8,
                    temperature=1.0,
                    max_new_tokens=100),
    max_out_len=100,
    max_seq_len=2048,
    batch_size=8,
    concurrency=8,
    meta_template=internlm_meta_template,
    run_cfg=dict(num_gpus=1, num_procs=1),
    end_str='<eoa>',
)

models = [internlm_chat_20b]