forked from chatchat-space/Langchain-Chatchat
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathmodel_config.py.example
More file actions
241 lines (207 loc) · 9.84 KB
/
model_config.py.example
File metadata and controls
241 lines (207 loc) · 9.84 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
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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
import os
# 可以指定一个绝对路径，统一存放所有的Embedding和LLM模型。
# 每个模型可以是一个单独的目录，也可以是某个目录下的二级子目录
MODEL_ROOT_PATH = ""
# 在以下字典中修改属性值，以指定本地embedding模型存储位置。支持3种设置方法：
# 1、将对应的值修改为模型绝对路径
# 2、不修改此处的值（以 text2vec 为例）：
# 2.1 如果{MODEL_ROOT_PATH}下存在如下任一子目录：
# - text2vec
# - GanymedeNil/text2vec-large-chinese
# - text2vec-large-chinese
# 2.2 如果以上本地路径不存在，则使用huggingface模型
MODEL_PATH = {
"embed_model": {
"ernie-tiny": "nghuyong/ernie-3.0-nano-zh",
"ernie-base": "nghuyong/ernie-3.0-base-zh",
"text2vec-base": "shibing624/text2vec-base-chinese",
"text2vec": "GanymedeNil/text2vec-large-chinese",
"text2vec-paraphrase": "shibing624/text2vec-base-chinese-paraphrase",
"text2vec-sentence": "shibing624/text2vec-base-chinese-sentence",
"text2vec-multilingual": "shibing624/text2vec-base-multilingual",
"text2vec-bge-large-chinese": "shibing624/text2vec-bge-large-chinese",
"m3e-small": "moka-ai/m3e-small",
"m3e-base": "moka-ai/m3e-base",
"m3e-large": "moka-ai/m3e-large",
"bge-small-zh": "BAAI/bge-small-zh",
"bge-base-zh": "BAAI/bge-base-zh",
"bge-large-zh": "BAAI/bge-large-zh",
"bge-large-zh-noinstruct": "BAAI/bge-large-zh-noinstruct",
"bge-base-zh-v1.5": "BAAI/bge-base-zh-v1.5",
"bge-large-zh-v1.5": "BAAI/bge-large-zh-v1.5",
"piccolo-base-zh": "sensenova/piccolo-base-zh",
"piccolo-large-zh": "sensenova/piccolo-large-zh",
"text-embedding-ada-002": "your OPENAI_API_KEY",
},
# TODO: add all supported llm models
"llm_model": {
# 以下部分模型并未完全测试，仅根据fastchat和vllm模型的模型列表推定支持
"chatglm-6b": "THUDM/chatglm-6b",
"chatglm2-6b": "THUDM/chatglm2-6b",
"chatglm2-6b-int4": "THUDM/chatglm2-6b-int4",
"chatglm2-6b-32k": "THUDM/chatglm2-6b-32k",
"baichuan2-13b": "baichuan-inc/Baichuan-13B-Chat",
"baichuan2-7b":"baichuan-inc/Baichuan2-7B-Chat",
"baichuan-7b": "baichuan-inc/Baichuan-7B",
"baichuan-13b": "baichuan-inc/Baichuan-13B",
'baichuan-13b-chat':'baichuan-inc/Baichuan-13B-Chat',
"aquila-7b":"BAAI/Aquila-7B",
"aquilachat-7b":"BAAI/AquilaChat-7B",
"internlm-7b":"internlm/internlm-7b",
"internlm-chat-7b":"internlm/internlm-chat-7b",
"falcon-7b":"tiiuae/falcon-7b",
"falcon-40b":"tiiuae/falcon-40b",
"falcon-rw-7b":"tiiuae/falcon-rw-7b",
"gpt2":"gpt2",
"gpt2-xl":"gpt2-xl",
"gpt-j-6b":"EleutherAI/gpt-j-6b",
"gpt4all-j":"nomic-ai/gpt4all-j",
"gpt-neox-20b":"EleutherAI/gpt-neox-20b",
"pythia-12b":"EleutherAI/pythia-12b",
"oasst-sft-4-pythia-12b-epoch-3.5":"OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
"dolly-v2-12b":"databricks/dolly-v2-12b",
"stablelm-tuned-alpha-7b":"stabilityai/stablelm-tuned-alpha-7b",
"Llama-2-13b-hf":"meta-llama/Llama-2-13b-hf",
"Llama-2-70b-hf":"meta-llama/Llama-2-70b-hf",
"open_llama_13b":"openlm-research/open_llama_13b",
"vicuna-13b-v1.3":"lmsys/vicuna-13b-v1.3",
"koala":"young-geng/koala",
"mpt-7b":"mosaicml/mpt-7b",
"mpt-7b-storywriter":"mosaicml/mpt-7b-storywriter",
"mpt-30b":"mosaicml/mpt-30b",
"opt-66b":"facebook/opt-66b",
"opt-iml-max-30b":"facebook/opt-iml-max-30b",
"Qwen-7B":"Qwen/Qwen-7B",
"Qwen-14B":"Qwen/Qwen-14B",
"Qwen-7B-Chat":"Qwen/Qwen-7B-Chat",
"Qwen-14B-Chat":"Qwen/Qwen-14B-Chat",
},
}
# 选用的 Embedding 名称
EMBEDDING_MODEL = "m3e-base" # 可以尝试最新的嵌入式sota模型：piccolo-large-zh
# Embedding 模型运行设备。设为"auto"会自动检测，也可手动设定为"cuda","mps","cpu"其中之一。
EMBEDDING_DEVICE = "auto"
# LLM 名称
LLM_MODEL = "chatglm2-6b"
# LLM 运行设备。设为"auto"会自动检测，也可手动设定为"cuda","mps","cpu"其中之一。
LLM_DEVICE = "auto"
# 历史对话轮数
HISTORY_LEN = 3
# LLM通用对话参数
TEMPERATURE = 0.7
# TOP_P = 0.95 # ChatOpenAI暂不支持该参数
ONLINE_LLM_MODEL = {
# 调用chatgpt时如果报出： urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='api.openai.com', port=443):
# Max retries exceeded with url: /v1/chat/completions
# 则需要将urllib3版本修改为1.25.11
# 如果依然报urllib3.exceptions.MaxRetryError: HTTPSConnectionPool，则将https改为http
# 参考https://zhuanlan.zhihu.com/p/350015032
# 如果报出：raise NewConnectionError(
# urllib3.exceptions.NewConnectionError: <urllib3.connection.HTTPSConnection object at 0x000001FE4BDB85E0>:
# Failed to establish a new connection: [WinError 10060]
# 则是因为内地和香港的IP都被OPENAI封了，需要切换为日本、新加坡等地
# 如果出现WARNING: Retrying langchain.chat_models.openai.acompletion_with_retry.<locals>._completion_with_retry in
# 4.0 seconds as it raised APIConnectionError: Error communicating with OpenAI.
# 需要添加代理访问(正常开的代理软件可能会拦截不上)需要设置配置openai_proxy 或者 使用环境遍历OPENAI_PROXY 进行设置
# 比如: "openai_proxy": 'http://127.0.0.1:4780'
"gpt-3.5-turbo": {
"api_base_url": "https://api.openai.com/v1",
"api_key": "your OPENAI_API_KEY",
"openai_proxy": "your OPENAI_PROXY",
},
# 线上模型。请在server_config中为每个在线API设置不同的端口
# 具体注册及api key获取请前往 http://open.bigmodel.cn
"zhipu-api": {
"api_key": "",
"version": "chatglm_pro", # 可选包括 "chatglm_lite", "chatglm_std", "chatglm_pro"
"provider": "ChatGLMWorker",
},
# 具体注册及api key获取请前往 https://api.minimax.chat/
"minimax-api": {
"group_id": "",
"api_key": "",
"is_pro": False,
"provider": "MiniMaxWorker",
},
# 具体注册及api key获取请前往 https://xinghuo.xfyun.cn/
"xinghuo-api": {
"APPID": "",
"APISecret": "",
"api_key": "",
"is_v2": False,
"provider": "XingHuoWorker",
},
# 百度千帆 API，申请方式请参考 https://cloud.baidu.com/doc/WENXINWORKSHOP/s/4lilb2lpf
"qianfan-api": {
"version": "ernie-bot-turbo", # 当前支持 "ernie-bot" 或 "ernie-bot-turbo"， 更多的见官方文档。
"version_url": "", # 也可以不填写version，直接填写在千帆申请模型发布的API地址
"api_key": "",
"secret_key": "",
"provider": "QianFanWorker",
},
# 火山方舟 API，文档参考 https://www.volcengine.com/docs/82379
"fangzhou-api": {
"version": "chatglm-6b-model", # 当前支持 "chatglm-6b-model"， 更多的见文档模型支持列表中方舟部分。
"version_url": "", # 可以不填写version，直接填写在方舟申请模型发布的API地址
"api_key": "",
"secret_key": "",
"provider": "FangZhouWorker",
},
# 阿里云通义千问 API，文档参考 https://help.aliyun.com/zh/dashscope/developer-reference/api-details
"qwen-api": {
"version": "qwen-turbo", # 可选包括 "qwen-turbo", "qwen-plus"
"api_key": "", # 请在阿里云控制台模型服务灵积API-KEY管理页面创建
"provider": "QwenWorker",
},
# 百川 API，申请方式请参考 https://www.baichuan-ai.com/home#api-enter
"baichuan-api": {
"version": "Baichuan2-53B", # 当前支持 "Baichuan2-53B"， 见官方文档。
"api_key": "",
"secret_key": "",
"provider": "BaiChuanWorker",
},
}
# 通常情况下不需要更改以下内容
# nltk 模型存储路径
NLTK_DATA_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "nltk_data")
VLLM_MODEL_DICT = {
"aquila-7b":"BAAI/Aquila-7B",
"aquilachat-7b":"BAAI/AquilaChat-7B",
"baichuan-7b": "baichuan-inc/Baichuan-7B",
"baichuan-13b": "baichuan-inc/Baichuan-13B",
'baichuan-13b-chat':'baichuan-inc/Baichuan-13B-Chat',
# 注意：bloom系列的tokenizer与model是分离的，因此虽然vllm支持，但与fschat框架不兼容
# "bloom":"bigscience/bloom",
# "bloomz":"bigscience/bloomz",
# "bloomz-560m":"bigscience/bloomz-560m",
# "bloomz-7b1":"bigscience/bloomz-7b1",
# "bloomz-1b7":"bigscience/bloomz-1b7",
"internlm-7b":"internlm/internlm-7b",
"internlm-chat-7b":"internlm/internlm-chat-7b",
"falcon-7b":"tiiuae/falcon-7b",
"falcon-40b":"tiiuae/falcon-40b",
"falcon-rw-7b":"tiiuae/falcon-rw-7b",
"gpt2":"gpt2",
"gpt2-xl":"gpt2-xl",
"gpt-j-6b":"EleutherAI/gpt-j-6b",
"gpt4all-j":"nomic-ai/gpt4all-j",
"gpt-neox-20b":"EleutherAI/gpt-neox-20b",
"pythia-12b":"EleutherAI/pythia-12b",
"oasst-sft-4-pythia-12b-epoch-3.5":"OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
"dolly-v2-12b":"databricks/dolly-v2-12b",
"stablelm-tuned-alpha-7b":"stabilityai/stablelm-tuned-alpha-7b",
"Llama-2-13b-hf":"meta-llama/Llama-2-13b-hf",
"Llama-2-70b-hf":"meta-llama/Llama-2-70b-hf",
"open_llama_13b":"openlm-research/open_llama_13b",
"vicuna-13b-v1.3":"lmsys/vicuna-13b-v1.3",
"koala":"young-geng/koala",
"mpt-7b":"mosaicml/mpt-7b",
"mpt-7b-storywriter":"mosaicml/mpt-7b-storywriter",
"mpt-30b":"mosaicml/mpt-30b",
"opt-66b":"facebook/opt-66b",
"opt-iml-max-30b":"facebook/opt-iml-max-30b",
"Qwen-7B":"Qwen/Qwen-7B",
"Qwen-14B":"Qwen/Qwen-14B",
"Qwen-7B-Chat":"Qwen/Qwen-7B-Chat",
"Qwen-14B-Chat":"Qwen/Qwen-14B-Chat",
}