forked from InternLM/lmdeploy
-
Notifications
You must be signed in to change notification settings - Fork 1
/
config-v100.yaml
149 lines (136 loc) · 4.37 KB
/
config-v100.yaml
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
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
model_path: /nvme/qa_test_models
dst_path: /nvme/qa_test_models/autotest_model
log_path: /nvme/qa_test_models/autotest_model/log
benchmark_path: /nvme/qa_test_models/benchmark-reports
dataset_path: /nvme/qa_test_models/datasets/ShareGPT_V3_unfiltered_cleaned_split.json
tp_config:
internlm-chat-20b: 2
internlm2-chat-20b: 2
Baichuan2-13B-Chat: 2
Mixtral-8x7B-Instruct-v0.1: 2
Qwen-VL-Chat: 2
llava-v1.5-13b: 2
internlm2_5-20b-chat: 2
internlm2_5-20b: 2
Meta-Llama-3-1-70B-Instruct: 4
internlm2_5-7b-chat-1m: 4
Qwen2-7B-Instruct-GPTQ-Int4: 2
InternVL2-26B: 2
InternVL2-40B: 2
MiniCPM-V-2_6: 2
turbomind_chat_model:
- meta-llama/Llama-3.2-1B-Instruct
- meta-llama/Llama-3.2-3B-Instruct
- meta-llama/Meta-Llama-3-1-8B-Instruct
- meta-llama/Meta-Llama-3-1-8B-Instruct-AWQ
- meta-llama/Meta-Llama-3-8B-Instruct
- meta-llama/Meta-Llama-3-8B-Instruct-inner-4bits
- internlm/internlm2_5-7b-chat
- internlm/internlm2_5-20b-chat
- internlm/internlm-xcomposer2d5-7b
- OpenGVLab/InternVL2-1B
- OpenGVLab/InternVL2-2B
- OpenGVLab/InternVL2-8B
- OpenGVLab/InternVL2-26B
- OpenGVLab/Mini-InternVL-Chat-2B-V1-5
- Qwen/Qwen2.5-0.5B-Instruct
- Qwen/Qwen2-7B-Instruct-AWQ
- Qwen/Qwen2-1.5B-Instruct
- Qwen/Qwen2.5-7B-Instruct
- Qwen/Qwen2-7B-Instruct-GPTQ-Int4
- mistralai/Mistral-7B-Instruct-v0.3
- THUDM/glm-4-9b-chat
pytorch_chat_model:
- meta-llama/Meta-Llama-3-8B-Instruct
- meta-llama/Meta-Llama-3-1-8B-Instruct
- internlm/internlm2_5-7b-chat
- internlm/internlm2_5-20b-chat
- OpenGVLab/InternVL2-1B
- OpenGVLab/InternVL2-2B
- OpenGVLab/InternVL2-4B
- OpenGVLab/InternVL2-8B
- OpenGVLab/InternVL2-26B
- Qwen/Qwen2-1.5B-Instruct
- Qwen/Qwen1.5-MoE-A2.7B-Chat
- Qwen/Qwen2-VL-2B-Instruct
- Qwen/Qwen2-VL-7B-Instruct
- google/gemma-2-9b-it
- mistralai/Mistral-7B-Instruct-v0.3
- THUDM/glm-4v-9b
- THUDM/glm-4-9b-chat
- microsoft/Phi-3-mini-4k-instruct
- deepseek-ai/DeepSeek-V2-Lite-Chat
turbomind_base_model:
- internlm/internlm2_5-7b
- internlm/internlm2_5-20b
pytorch_base_model:
- internlm/internlm2_5-7b
- internlm/internlm2_5-20b
turbomind_vl_model:
- OpenGVLab/InternVL2-1B
- OpenGVLab/InternVL2-2B
- OpenGVLab/InternVL2-8B
- OpenGVLab/InternVL2-26B
- Qwen/Qwen2-VL-2B-Instruct
- Qwen/Qwen2-VL-7B-Instruct
- internlm/internlm-xcomposer2d5-7b
- THUDM/glm-4v-9b
pytorch_vl_model:
- OpenGVLab/InternVL2-1B
- OpenGVLab/InternVL2-4B
- OpenGVLab/InternVL2-8B
- OpenGVLab/InternVL2-26B
- OpenGVLab/Mono-InternVL-2B
- Qwen/Qwen2-VL-2B-Instruct
- Qwen/Qwen2-VL-7B-Instruct
- THUDM/glm-4v-9b
- microsoft/Phi-3.5-vision-instruct
turbomind_quatization:
no_awq:
- meta-llama/Meta-Llama-3-1-8B-Instruct
- meta-llama/Meta-Llama-3-8B-Instruct
- internlm/internlm-xcomposer2d5-7b
- OpenGVLab/Mini-InternVL-Chat-2B-V1-5
- mistralai/Mistral-7B-Instruct-v0.3
- THUDM/glm-4-9b-chat
gptq:
- internlm/internlm2_5-7b-chat
no_kvint4:
- openbmb/MiniCPM-V-2_6
no_kvint8:
- deepseek-ai/DeepSeek-V2-Lite-Chat
pytorch_quatization:
awq:
- internlm/internlm2_5-7b-chat
- internlm/internlm2_5-20b-chat
- Qwen/Qwen2-1.5B-Instruct
w8a8:
- internlm/internlm2_5-7b-chat
- internlm/internlm2_5-7b
no_kvint4:
- OpenGVLab/InternVL2-1B
- OpenGVLab/InternVL2-4B
- deepseek-ai/DeepSeek-V2-Lite-Chat
- microsoft/Phi-3-mini-4k-instruct
- microsoft/Phi-3-vision-128k-instruct
- microsoft/Phi-3.5-vision-instruct
- openbmb/MiniCPM-V-2_6
no_kvint8:
- deepseek-ai/DeepSeek-V2-Lite-Chat
longtext_model:
- meta-llama/Meta-Llama-3-1-8B-Instruct
- meta-llama/Meta-Llama-3-8B-Instruct
- meta-llama/Meta-Llama-3-1-70B-Instruct
- internlm/internlm2_5-7b-chat-1m
- internlm/internlm2-chat-20b
benchmark_model:
- meta-llama/Llama-2-7b-chat-hf
- meta-llama/Meta-Llama-3-1-8B-Instruct
- meta-llama/Meta-Llama-3-8B-Instruct
- meta-llama/Meta-Llama-3-1-70B-Instruct
- internlm/internlm2_5-7b-chat
- internlm/internlm2_5-20b-chat
- THUDM/glm-4-9b-chat
- mistralai/Mistral-7B-Instruct-v0.3
- mistralai/Mixtral-8x7B-Instruct-v0.1
- deepseek-ai/DeepSeek-V2-Lite-Chat