From a938b67163dd5d2f03ae8e9847e23ef71449047f Mon Sep 17 00:00:00 2001 From: imClumsyPanda Date: Sun, 5 Nov 2023 11:17:09 +0800 Subject: [PATCH] reformat config files --- configs/kb_config.py.example | 4 +- configs/model_config.py.example | 154 +++++++++++++++---------------- configs/prompt_config.py.example | 78 ++++++++-------- 3 files changed, 118 insertions(+), 118 deletions(-) diff --git a/configs/kb_config.py.example b/configs/kb_config.py.example index e125c84..4e9cfe2 100644 --- a/configs/kb_config.py.example +++ b/configs/kb_config.py.example @@ -117,5 +117,5 @@ text_splitter_dict = { # TEXT_SPLITTER 名称 TEXT_SPLITTER_NAME = "ChineseRecursiveTextSplitter" -## Embedding模型定制词语的词表文件 -EMBEDDING_KEYWORD_FILE = "embedding_keywords.txt" \ No newline at end of file +# Embedding模型定制词语的词表文件 +EMBEDDING_KEYWORD_FILE = "embedding_keywords.txt" diff --git a/configs/model_config.py.example b/configs/model_config.py.example index a105708..4419df0 100644 --- a/configs/model_config.py.example +++ b/configs/model_config.py.example @@ -1,6 +1,5 @@ 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 = "" @@ -45,54 +44,53 @@ MODEL_PATH = { "chatglm3-6b-32k": "THUDM/chatglm3-6b-32k", "baichuan2-13b": "baichuan-inc/Baichuan2-13B-Chat", - "baichuan2-7b":"baichuan-inc/Baichuan2-7B-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', + 'baichuan-13b-chat': 'baichuan-inc/Baichuan-13B-Chat', - "aquila-7b":"BAAI/Aquila-7B", - "aquilachat-7b":"BAAI/AquilaChat-7B", + "aquila-7b": "BAAI/Aquila-7B", + "aquilachat-7b": "BAAI/AquilaChat-7B", - "internlm-7b":"internlm/internlm-7b", - "internlm-chat-7b":"internlm/internlm-chat-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", + "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", + "gpt2": "gpt2", + "gpt2-xl": "gpt2-xl", - "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", + "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", - "Qwen-7B":"Qwen/Qwen-7B", - "Qwen-14B":"Qwen/Qwen-14B", - "Qwen-7B-Chat":"Qwen/Qwen-7B-Chat", - "Qwen-14B-Chat":"Qwen/Qwen-14B-Chat", + "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_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" @@ -147,13 +145,13 @@ ONLINE_LLM_MODEL = { "APPID": "", "APISecret": "", "api_key": "", - "version": "v1.5", # 你使用的讯飞星火大模型版本，可选包括 "v3.0", "v1.5", "v2.0" + "version": "v1.5", # 你使用的讯飞星火大模型版本，可选包括 "v3.0", "v1.5", "v2.0" "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", # 注意大小写。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 + "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", @@ -183,28 +181,26 @@ ONLINE_LLM_MODEL = { # Azure API "azure-api": { - "deployment_name": "", # 部署容器的名字 - "resource_name": "", # https://{resource_name}.openai.azure.com/openai/ 填写resource_name的部分，其他部分不要填写 - "api_version": "", # API的版本，不是模型版本 + "deployment_name": "", # 部署容器的名字 + "resource_name": "", # https://{resource_name}.openai.azure.com/openai/ 填写resource_name的部分，其他部分不要填写 + "api_version": "", # API的版本，不是模型版本 "api_key": "", "provider": "AzureWorker", }, } - # 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", + "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', + '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", @@ -212,43 +208,43 @@ VLLM_MODEL_DICT = { # "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", + "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", + "Qwen-7B": "Qwen/Qwen-7B", + "Qwen-14B": "Qwen/Qwen-14B", + "Qwen-7B-Chat": "Qwen/Qwen-7B-Chat", + "Qwen-14B-Chat": "Qwen/Qwen-14B-Chat", - "agentlm-7b":"THUDM/agentlm-7b", - "agentlm-13b":"THUDM/agentlm-13b", - "agentlm-70b":"THUDM/agentlm-70b", + "agentlm-7b": "THUDM/agentlm-7b", + "agentlm-13b": "THUDM/agentlm-13b", + "agentlm-70b": "THUDM/agentlm-70b", } -## 你认为支持Agent能力的模型，可以在这里添加，添加后不会出现可视化界面的警告 +# 你认为支持Agent能力的模型，可以在这里添加，添加后不会出现可视化界面的警告 SUPPORT_AGENT_MODEL = [ "azure-api", "openai-api", diff --git a/configs/prompt_config.py.example b/configs/prompt_config.py.example index 85f0986..d645725 100644 --- a/configs/prompt_config.py.example +++ b/configs/prompt_config.py.example @@ -17,64 +17,65 @@ # - input: 用户输入内容 # - agent_scratchpad: Agent的思维记录 -PROMPT_TEMPLATES = {} +PROMPT_TEMPLATES = { + "completion": { + "default": "{input}" + }, -PROMPT_TEMPLATES["completion"] = { - "default": "{input}" -} + "llm_chat": { + "default": "{{ input }}", -PROMPT_TEMPLATES["llm_chat"] = { - "default": "{{ input }}", - - "py": - """ - 你是一个聪明的代码助手，请你给我写出简单的py代码。 \n - {{ input }} - """ - , -} - -PROMPT_TEMPLATES["knowledge_base_chat"] = { - "default": + "py": + """ + 你是一个聪明的代码助手，请你给我写出简单的py代码。 \n + {{ input }} """ + , + }, + + "knowledge_base_chat": { + "default": + """ <指令>根据已知信息，简洁和专业的来回答问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题”，不允许在答案中添加编造成分，答案请使用中文。 <已知信息>{{ context }}、 <问题>{{ question }} """, - "text": - """ + "text": + """ <指令>根据已知信息，简洁和专业的来回答问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题”，答案请使用中文。 <已知信息>{{ context }}、 <问题>{{ question }} """, - "Empty": # 搜不到内容的时候调用，此时没有已知信息，这个Empty可以更改，但不能删除，会影响程序使用 - """ + "Empty": # 搜不到内容的时候调用，此时没有已知信息，这个Empty可以更改，但不能删除，会影响程序使用 + """ <指令>请根据用户的问题，进行简洁明了的回答 <问题>{{ question }} """, -} -PROMPT_TEMPLATES["search_engine_chat"] = { - "default": - """ + }, + + "search_engine_chat": { + "default": + """ <指令>这是我搜索到的互联网信息，请你根据这些信息进行提取并有调理，简洁的回答问题。如果无法从中得到答案，请说 “无法搜索到能回答问题的内容”。 <已知信息>{{ context }}、 <问题>{{ question }} """, - "search": - """ + "search": + """ <指令>根据已知信息，简洁和专业的来回答问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题”，答案请使用中文。 <已知信息>{{ context }}、 <问题>{{ question }} """, - "Empty": # 搜不到内容的时候调用，此时没有已知信息，这个Empty可以更改，但不能删除，会影响程序使用 - """ + "Empty": # 搜不到内容的时候调用，此时没有已知信息，这个Empty可以更改，但不能删除，会影响程序使用 + """ <指令>请根据用户的问题，进行简洁明了的回答 <问题>{{ question }} """, -} -PROMPT_TEMPLATES["agent_chat"] = { - "default": - """ + }, + + "agent_chat": { + "default": + """ Answer the following questions as best you can. If it is in order, you can use some tools appropriately.You have access to the following tools: {tools} @@ -99,8 +100,9 @@ PROMPT_TEMPLATES["agent_chat"] = { Question: {input} Thought: {agent_scratchpad} """, - "AgentLM": - """ + + "AgentLM": + """ >\n You are a helpful, respectful and honest assistant. >\n @@ -125,8 +127,9 @@ PROMPT_TEMPLATES["agent_chat"] = { Thought: {agent_scratchpad} """, - "中文版本": - """ + + "中文版本": + """ 你的知识不一定正确，所以你一定要用提供的工具来思考，并给出用户答案。 你有以下工具可以使用: {tools} @@ -151,4 +154,5 @@ PROMPT_TEMPLATES["agent_chat"] = { Question: {input} Thought: {agent_scratchpad} """, + }, }