-
Notifications
You must be signed in to change notification settings - Fork 573
/
models.py
95 lines (89 loc) · 2.51 KB
/
models.py
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
import os
from dotenv import load_dotenv
from lagent.llms import (
GPTAPI,
INTERNLM2_META,
HFTransformerCasualLM,
LMDeployClient,
LMDeployServer,
)
internlm_server = dict(
type=LMDeployServer,
path="internlm/internlm2_5-7b-chat",
model_name="internlm2_5-7b-chat",
meta_template=INTERNLM2_META,
top_p=0.8,
top_k=1,
temperature=0,
max_new_tokens=8192,
repetition_penalty=1.02,
stop_words=["<|im_end|>"],
)
internlm_client = dict(
type=LMDeployClient,
model_name="internlm2_5-7b-chat",
url="http://127.0.0.1:23333",
meta_template=INTERNLM2_META,
top_p=0.8,
top_k=1,
temperature=0,
max_new_tokens=8192,
repetition_penalty=1.02,
stop_words=["<|im_end|>"],
)
internlm_hf = dict(
type=HFTransformerCasualLM,
path="internlm/internlm2_5-7b-chat",
meta_template=INTERNLM2_META,
top_p=0.8,
top_k=None,
temperature=1e-6,
max_new_tokens=8192,
repetition_penalty=1.02,
stop_words=["<|im_end|>"],
)
# openai_api_base needs to fill in the complete chat api address, such as: https://api.openai.com/v1/chat/completions
gpt4 = dict(
type=GPTAPI,
model_type="gpt-4-turbo",
key=os.environ.get("OPENAI_API_KEY", "YOUR OPENAI API KEY"),
api_base=os.environ.get("OPENAI_API_BASE",
"https://api.openai.com/v1/chat/completions"),
)
url = "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation"
qwen = dict(
type=GPTAPI,
model_type="qwen-max-longcontext",
key=os.environ.get("QWEN_API_KEY", "YOUR QWEN API KEY"),
api_base=url,
meta_template=[
dict(role="system", api_role="system"),
dict(role="user", api_role="user"),
dict(role="assistant", api_role="assistant"),
dict(role="environment", api_role="system"),
],
top_p=0.8,
top_k=1,
temperature=0,
max_new_tokens=4096,
repetition_penalty=1.02,
stop_words=["<|im_end|>"],
)
internlm_silicon = dict(
type=GPTAPI,
model_type="internlm/internlm2_5-7b-chat",
key=os.environ.get("SILICON_API_KEY", "YOUR SILICON API KEY"),
api_base="https://api.siliconflow.cn/v1/chat/completions",
meta_template=[
dict(role="system", api_role="system"),
dict(role="user", api_role="user"),
dict(role="assistant", api_role="assistant"),
dict(role="environment", api_role="system"),
],
top_p=0.8,
top_k=1,
temperature=0,
max_new_tokens=8192,
repetition_penalty=1.02,
stop_words=["<|im_end|>"],
)