weiweiw
/
Langchain-Chatchat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

reformat config files

This commit is contained in:
imClumsyPanda 2023-11-05 11:17:09 +08:00
parent 5e0476925b
commit a938b67163
3 changed files with 118 additions and 118 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
configs/kb_config.py.example
View File

@ -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模型定制词语的词表文件
EMBEDDING_KEYWORD_FILE = "embedding_keywords.txt"

138
configs/model_config.py.example
View File

@ -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 = ""
@ -45,55 +44,54 @@ 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",
"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",
"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",
"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",
"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",
},
}
# 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"
@ -191,20 +189,18 @@ ONLINE_LLM_MODEL = {
},
}
# 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",

26
configs/prompt_config.py.example
View File

@ -17,13 +17,12 @@
# - input: 用户输入内容
# - agent_scratchpad: Agent的思维记录
PROMPT_TEMPLATES = {}
PROMPT_TEMPLATES["completion"] = {
PROMPT_TEMPLATES = {
"completion": {
"default": "{input}"
}
},
PROMPT_TEMPLATES["llm_chat"] = {
"llm_chat": {
"default": "{{ input }}",
"py":
@ -32,9 +31,9 @@ PROMPT_TEMPLATES["llm_chat"] = {
{{ input }}
"""
,
}
},
PROMPT_TEMPLATES["knowledge_base_chat"] = {
"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。 </指令>
@ -52,8 +51,9 @@ PROMPT_TEMPLATES["knowledge_base_chat"] = {
<指令>请根据用户的问题，进行简洁明了的回答</指令>
<问题>{{ question }}</问题>
""",
}
PROMPT_TEMPLATES["search_engine_chat"] = {
},
"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”。 </指令>
@ -71,8 +71,9 @@ PROMPT_TEMPLATES["search_engine_chat"] = {
<指令>请根据用户的问题，进行简洁明了的回答</指令>
<问题>{{ question }}</问题>
""",
}
PROMPT_TEMPLATES["agent_chat"] = {
},
"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:
@ -99,6 +100,7 @@ PROMPT_TEMPLATES["agent_chat"] = {
Question: {input}
Thought: {agent_scratchpad}
""",
"AgentLM":
"""
<SYS>>\n
@ -125,6 +127,7 @@ PROMPT_TEMPLATES["agent_chat"] = {
Thought: {agent_scratchpad}
""",
"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。
@ -151,4 +154,5 @@ PROMPT_TEMPLATES["agent_chat"] = {
Question: {input}
Thought: {agent_scratchpad}
""",
},
}