260 lines
11 KiB
Python
260 lines
11 KiB
Python
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",
|
||
"chatglm3-6b": "THUDM/chatglm3-6b",
|
||
"chatglm2-6b-int4": "THUDM/chatglm2-6b-int4",
|
||
"chatglm2-6b-32k": "THUDM/chatglm2-6b-32k",
|
||
|
||
"baichuan2-13b": "baichuan-inc/Baichuan2-13B-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：bge-large-zh-v1.5
|
||
|
||
|
||
# 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
|
||
|
||
|
||
LANGCHAIN_LLM_MODEL = {
|
||
# 不需要走Fschat封装的，Langchain直接支持的模型。
|
||
# 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'
|
||
|
||
# 这些配置文件的名字不能改动
|
||
"Azure-OpenAI": {
|
||
"deployment_name": "your Azure deployment name",
|
||
"model_version": "0701",
|
||
"openai_api_type": "azure",
|
||
"api_base_url": "https://your Azure point.azure.com",
|
||
"api_version": "2023-07-01-preview",
|
||
"api_key": "your Azure api key",
|
||
"openai_proxy": "",
|
||
},
|
||
"OpenAI": {
|
||
"model_name": "your openai model name(such as gpt-4)",
|
||
"api_base_url": "https://api.openai.com/v1",
|
||
"api_key": "your OPENAI_API_KEY",
|
||
"openai_proxy": "",
|
||
},
|
||
"Anthropic": {
|
||
"model_name": "your claude model name(such as claude2-100k)",
|
||
"api_key":"your ANTHROPIC_API_KEY",
|
||
}
|
||
}
|
||
ONLINE_LLM_MODEL = {
|
||
# 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",
|
||
|
||
} |