Skip to content

GitLab

Commit dfe42ac1 authored by lvzhen's avatar lvzhen
Browse files

Update DEPLOYMENT_en.md, MODEL_LICENSE, PROMPT.md, PROMPT_en.md, README.md,... 

Update DEPLOYMENT_en.md, MODEL_LICENSE, PROMPT.md, PROMPT_en.md, README.md, README_en.md, requirements.txt, .gitignore, LICENSE, update_requirements.sh files
Deleted lvzhen.log, basic_demo/cli_demo.py, basic_demo/cli_demo_bad_word_ids.py, basic_demo/infer_test.py, basic_demo/utils.py, basic_demo/vocab.txt, basic_demo/web_demo.py, basic_demo/web_demo2.py, composite_demo/.streamlit/config.toml, composite_demo/assets/demo.png, composite_demo/assets/emojis.png, composite_demo/assets/heart.png, composite_demo/assets/tool.png, composite_demo/README.md, composite_demo/README_en.md, composite_demo/client.py, composite_demo/conversation.py, composite_demo/demo_chat.py, composite_demo/demo_ci.py, composite_demo/demo_tool.py, composite_demo/main.py, composite_demo/requirements.txt, composite_demo/tool_registry.py, cookbook/data/toutiao_cat_data_example.txt, cookbook/accurate_prompt.ipynb, cookbook/finetune_muti_classfication.ipynb, finetune_basemodel_demo/scripts/finetune_lora.sh, finetune_basemodel_demo/scripts/formate_alpaca2jsonl.py, finetune_basemodel_demo/README.md, finetune_basemodel_demo/arguments.py, finetune_basemodel_demo/finetune.py, finetune_basemodel_demo/inference.py, finetune_basemodel_demo/preprocess_utils.py, finetune_basemodel_demo/requirements.txt, finetune_basemodel_demo/trainer.py, finetune_chatmodel_demo/AdvertiseGen/dev.json, finetune_chatmodel_demo/AdvertiseGen/train.json, finetune_chatmodel_demo/configs/deepspeed.json, finetune_chatmodel_demo/formatted_data/advertise_gen.jsonl, finetune_chatmodel_demo/formatted_data/tool_alpaca.jsonl, finetune_chatmodel_demo/scripts/finetune_ds.sh, finetune_chatmodel_demo/scripts/finetune_ds_multiturn.sh, finetune_chatmodel_demo/scripts/finetune_pt.sh, finetune_chatmodel_demo/scripts/finetune_pt_multiturn.sh, finetune_chatmodel_demo/scripts/format_advertise_gen.py, finetune_chatmodel_demo/scripts/format_tool_alpaca.py, finetune_chatmodel_demo/README.md, finetune_chatmodel_demo/arguments.py, finetune_chatmodel_demo/finetune.py, finetune_chatmodel_demo/inference.py, finetune_chatmodel_demo/preprocess_utils.py, finetune_chatmodel_demo/requirements.txt, finetune_chatmodel_demo/train_data.json, finetune_chatmodel_demo/trainer.py, langchain_demo/Tool/Calculator.py, langchain_demo/Tool/Calculator.yaml, langchain_demo/Tool/Weather.py, langchain_demo/Tool/arxiv_example.yaml, langchain_demo/Tool/weather.yaml, langchain_demo/ChatGLM3.py, langchain_demo/README.md, langchain_demo/main.py, langchain_demo/requirements.txt, langchain_demo/utils.py, media/GLM.png, media/cli.png, media/transformers.jpg, openai_api_demo/openai_api.py, openai_api_demo/openai_api_request.py, openai_api_demo/requirements.txt, openai_api_demo/utils.py, resources/WECHAT.md, resources/cli-demo.png, resources/code_en.gif, resources/heart.png, resources/tool.png, resources/tool_en.png, resources/web-demo.gif, resources/web-demo2.gif, resources/web-demo2.png, resources/wechat.jpg, tool_using/README.md, tool_using/README_en.md, tool_using/cli_demo_tool.py, tool_using/openai_api_demo.py, tool_using/requirements.txt, tool_using/test.py, tool_using/tool_register.py, Dockerfile, README_old.md, model.properties files
parent d7be7b1c
Pipeline #982 failed with stages
in 0 seconds
Hide whitespace changes
Inline Side-by-side
Showing with 38 additions and 484 deletions
requirements.txt
View file @ dfe42ac1
protobuf
pydantic==1.10.9
transformers==4.30.2
sentencepiece==0.1.99
accelerate==0.21.0
sse-starlette
astunparse==1.6.2
# basic requirements
protobuf>=4.25.3
transformers>=4.39.3
tokenizers>=0.15.0
cpm_kernels>=1.0.11
torch>=2.1.0
gradio>=4.26.0
sentencepiece>=0.2.0
sentence_transformers>=2.4.0
accelerate>=0.29.2
streamlit>=1.33.0
fastapi>=0.110.0
loguru~=0.7.2
mdtex2html>=1.3.0
latex2mathml>=3.77.0
jupyter_client>=8.6.1
# for openai demo
openai>=1.17.1
zhipuai>=2.0.1
pydantic>=2.7.0
sse-starlette>=2.0.0
uvicorn>=0.29.0
timm>=0.9.16
tiktoken>=0.6.0
# for langchain demo
langchain>=0.1.16
langchainhub>=0.1.15
arxiv>=2.1.0
\ No newline at end of file
resources/WECHAT.md deleted 100644 → 0
View file @ d7be7b1c
<div align="center">
<img src=wechat.jpg width="60%"/>
<p> 扫码关注公众号，加入「ChatGLM交流群」 </p>
<p> Scan the QR code to follow the official account and join the "ChatGLM Discussion Group" </p>
</div>
tool_using/README.md deleted 100644 → 0
View file @ d7be7b1c
# 工具调用
本文档将介绍如何使用 ChatGLM3-6B 进行工具调用。目前只有 ChatGLM3-6B 模型支持工具调用，而 ChatGLM3-6B-Base 和 ChatGLM3-6B-32K 模型不支持。
## 构建 System Prompt
这里以两个工具调用为例，首先准备好要构建的数据的描述信息。
```python
tools = [
{
"name": "track",
"description": "追踪指定股票的实时价格",
"parameters": {
"type": "object",
"properties": {
"symbol": {
"description": "需要追踪的股票代码"
}
},
"required": ['symbol']
}
},
{
"name": "text-to-speech",
"description": "将文本转换为语音",
"parameters": {
"type": "object",
"properties": {
"text": {
"description": "需要转换成语音的文本"
},
"voice": {
"description": "要使用的语音类型（男声、女声等）"
},
"speed": {
"description": "语音的速度（快、中等、慢等）"
}
},
"required": ['text']
}
}
]
system_info = {"role": "system", "content": "Answer the following questions as best as you can. You have access to the following tools:", "tools": tools}
```
请确保工具的定义格式与例子中一致以获得最优的性能
## 提出问题
注意：目前 ChatGLM3-6B 的工具调用只支持通过 `chat` 方法，不支持 `stream_chat` 方法。
```python
history = [system_info]
query = "帮我查询股票10111的价格"
response, history = model.chat(tokenizer, query, history=history)
print(response)
```
这里期望得到的输出为
```json
{"name": "track", "parameters": {"symbol": "10111"}}
```
这表示模型需要调用工具 `track`，并且需要传入参数 `symbol`。
## 调用工具，生成回复
这里需要自行实现调用工具的逻辑。假设已经得到了返回结果，将结果以 json 格式返回给模型并得到回复。
```python
result = json.dumps({"price": 12412}, ensure_ascii=False)
response, history = model.chat(tokenizer, result, history=history, role="observation")
print(response)
```
这里 `role="observation"` 表示输入的是工具调用的返回值而不是用户输入，不能省略。
期望得到的输出为
```
根据您的查询，经过API的调用，股票10111的价格是12412。
```
这表示本次工具调用已经结束，模型根据返回结果生成回复。对于比较复杂的问题，模型可能需要进行多次工具调用。这时，可以根据返回的 `response` 是 `str` 还是 `dict` 来判断返回的是生成的回复还是工具调用请求。
\ No newline at end of file
tool_using/README_en.md deleted 100644 → 0
View file @ d7be7b1c
# Tool Invocation
This document will introduce how to use the ChatGLM3-6B for tool invocation. Currently, only the ChatGLM3-6B model supports tool invocation, while the ChatGLM3-6B-Base and ChatGLM3-6B-32K models do not support it.
## Building System Prompt
Here are two examples of tool invocation. First, prepare the description information of the data to be built.
```python
tools = [
{
"name": "track",
"description": "Track the real-time price of a specified stock",
"parameters": {
"type": "object",
"properties": {
"symbol": {
"description": "The stock code that needs to be tracked"
}
},
"required": ['symbol']
}
},
{
"name": "text-to-speech",
"description": "Convert text to speech",
"parameters": {
"type": "object",
"properties": {
"text": {
"description": "The text that needs to be converted into speech"
},
"voice": {
"description": "The type of voice to use (male, female, etc.)"
},
"speed": {
"description": "The speed of the speech (fast, medium, slow, etc.)"
}
},
"required": ['text']
}
}
]
system_info = {"role": "system", "content": "Answer the following questions as best as you can. You have access to the following tools:", "tools": tools}
```
Please ensure that the definition format of the tool is consistent with the example to obtain optimal performance.
## Asking Questions
Note: Currently, the tool invocation of ChatGLM3-6B only supports the `chat` method and does not support the `stream_chat` method.
```python
history = [system_info]
query = "Help me inquire the price of stock 10111"
response, history = model.chat(tokenizer, query, history=history)
print(response)
```
The expected output here is
```json
{"name": "track", "parameters": {"symbol": "10111"}}
```
This indicates that the model needs to call the tool `track`, and the parameter `symbol` needs to be passed in.
## Invoke Tool, Generate Response
Here, you need to implement the logic of calling the tool yourself. Assuming that the return result has been obtained, return the result to the model in json format and get a response.
```python
result = json.dumps({"price": 12412}, ensure_ascii=False)
response, history = model.chat(tokenizer, result, history=history, role="observation")
print(response)
```
Here `role="observation"` indicates that the input is the return value of the tool invocation rather than user input, and it cannot be omitted.
The expected output is
```
Based on your query, after the API call, the price of stock 10111 is 12412.
```
This indicates that this tool invocation has ended, and the model generates a response based on the return result. For more complex questions, the model may need to make multiple tool invocations. At this time, you can judge whether the returned `response` is `str` or `dict` to determine whether the return is a generated response or a tool invocation request.
\ No newline at end of file
tool_using/cli_demo_tool.py deleted 100644 → 0
View file @ d7be7b1c
import os
import platform
from transformers import AutoTokenizer, AutoModel
import torch
MODEL_PATH = os.environ.get('MODEL_PATH', 'THUDM/chatglm3-6b')
TOKENIZER_PATH = os.environ.get("TOKENIZER_PATH", MODEL_PATH)
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
tokenizer = AutoTokenizer.from_pretrained(TOKENIZER_PATH, trust_remote_code=True)
if 'cuda' in DEVICE: # AMD, NVIDIA GPU can use Half Precision
model = AutoModel.from_pretrained(MODEL_PATH, trust_remote_code=True).to(DEVICE).eval()
else: # CPU, Intel GPU and other GPU can use Float16 Precision Only
model = AutoModel.from_pretrained(MODEL_PATH, trust_remote_code=True).float().to(DEVICE).eval()
os_name = platform.system()
clear_command = 'cls' if os_name == 'Windows' else 'clear'
stop_stream = False
def build_prompt(history):
prompt = "欢迎使用 ChatGLM3-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序"
for query, response in history:
prompt += f"\n\n用户：{query}"
prompt += f"\n\nChatGLM3-6B：{response}"
return prompt
tools = [{'name': 'track', 'description': '追踪指定股票的实时价格', 'parameters': {'type': 'object', 'properties': {'symbol': {'description': '需要追踪的股票代码'}}, 'required': []}}, {'name': '/text-to-speech', 'description': '将文本转换为语音', 'parameters': {'type': 'object', 'properties': {'text': {'description': '需要转换成语音的文本'}, 'voice': {'description': '要使用的语音类型（男声、女声等）'}, 'speed': {'description': '语音的速度（快、中等、慢等）'}}, 'required': []}}, {'name': '/image_resizer', 'description': '调整图片的大小和尺寸', 'parameters': {'type': 'object', 'properties': {'image_file': {'description': '需要调整大小的图片文件'}, 'width': {'description': '需要调整的宽度值'}, 'height': {'description': '需要调整的高度值'}}, 'required': []}}, {'name': '/foodimg', 'description': '通过给定的食品名称生成该食品的图片', 'parameters': {'type': 'object', 'properties': {'food_name': {'description': '需要生成图片的食品名称'}}, 'required': []}}]
system_item = {"role": "system",
"content": "Answer the following questions as best as you can. You have access to the following tools:",
"tools": tools}
def main():
past_key_values, history = None, [system_item]
role = "user"
global stop_stream
print("欢迎使用 ChatGLM3-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
while True:
query = input("\n用户：") if role == "user" else input("\n结果：")
if query.strip() == "stop":
break
if query.strip() == "clear":
past_key_values, history = None, [system_item]
role = "user"
os.system(clear_command)
print("欢迎使用 ChatGLM3-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
continue
print("\nChatGLM：", end="")
response, history = model.chat(tokenizer, query, history=history, role=role)
print(response, end="", flush=True)
print("")
if isinstance(response, dict):
role = "observation"
if __name__ == "__main__":
main()
\ No newline at end of file
tool_using/openai_api_demo.py deleted 100644 → 0
View file @ d7be7b1c
import json
from openai import OpenAI
from colorama import init, Fore
from loguru import logger
from tool_register import get_tools, dispatch_tool
init(autoreset=True)
client = OpenAI(
base_url="http://127.0.0.1:8000/v1",
api_key = "xxx"
)
functions = get_tools()
def run_conversation(query: str, stream=False, functions=None, max_retry=5):
params = dict(model="chatglm3", messages=[{"role": "user", "content": query}], stream=stream)
if functions:
params["functions"] = functions
response = client.chat.completions.create(**params)
for _ in range(max_retry):
if not stream:
if response.choices[0].message.function_call:
function_call = response.choices[0].message.function_call
logger.info(f"Function Call Response: {function_call.model_dump()}")
function_args = json.loads(function_call.arguments)
tool_response = dispatch_tool(function_call.name, function_args)
logger.info(f"Tool Call Response: {tool_response}")
params["messages"].append(response.choices[0].message)
params["messages"].append(
{
"role": "function",
"name": function_call.name,
"content": tool_response, # 调用函数返回结果
}
)
else:
reply = response.choices[0].message.content
logger.info(f"Final Reply: \n{reply}")
return
else:
output = ""
for chunk in response:
content = chunk.choices[0].delta.content or ""
print(Fore.BLUE + content, end="", flush=True)
output += content
if chunk.choices[0].finish_reason == "stop":
return
elif chunk.choices[0].finish_reason == "function_call":
print("\n")
function_call = chunk.choices[0].delta.function_call
logger.info(f"Function Call Response: {function_call.model_dump()}")
function_args = json.loads(function_call.arguments)
tool_response = dispatch_tool(function_call.name, function_args)
logger.info(f"Tool Call Response: {tool_response}")
params["messages"].append(
{
"role": "assistant",
"content": output
}
)
params["messages"].append(
{
"role": "function",
"name": function_call.name,
"content": tool_response, # 调用函数返回结果
}
)
break
response = client.chat.completions.create(**params)
if __name__ == "__main__":
query = "你是谁"
run_conversation(query, stream=True)
logger.info("\n=========== next conversation ===========")
query = "帮我查询北京的天气怎么样"
run_conversation(query, functions=functions, stream=True)
tool_using/test.py deleted 100644 → 0
View file @ d7be7b1c
tools = [
{
"name": "track",
"description": "追踪指定股票的实时价格",
"parameters": {
"type": "object",
"properties": {
"symbol": {
"description": "需要追踪的股票代码"
}
},
"required": ['symbol']
}
},
{
"name": "text-to-speech",
"description": "将文本转换为语音",
"parameters": {
"type": "object",
"properties": {
"text": {
"description": "需要转换成语音的文本"
},
"voice": {
"description": "要使用的语音类型（男声、女声等）"
},
"speed": {
"description": "语音的速度（快、中等、慢等）"
}
},
"required": ['text']
}
}
]
system_info = {"role": "system", "content": "Answer the following questions as best as you can. You have access to the following tools:", "tools": tools}
import os
import platform
from transformers import AutoTokenizer, AutoModel
import torch
MODEL_PATH = os.environ.get('MODEL_PATH', '../../chatglm3-6b')
TOKENIZER_PATH = os.environ.get("TOKENIZER_PATH", MODEL_PATH)
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
tokenizer = AutoTokenizer.from_pretrained(TOKENIZER_PATH, trust_remote_code=True)
if 'cuda' in DEVICE: # AMD, NVIDIA GPU can use Half Precision
model = AutoModel.from_pretrained(MODEL_PATH, trust_remote_code=True).to(DEVICE).eval()
else: # CPU, Intel GPU and other GPU can use Float16 Precision Only
model = AutoModel.from_pretrained(MODEL_PATH, trust_remote_code=True).float().to(DEVICE).eval()
history = [system_info]
query = "帮我查询股票10111的价格"
response, history = model.chat(tokenizer, query, history=history)
print(response)
\ No newline at end of file
tool_using/tool_register.py deleted 100644 → 0
View file @ d7be7b1c
import inspect
import traceback
from copy import deepcopy
from pprint import pformat
from types import GenericAlias
from typing import get_origin, Annotated
_TOOL_HOOKS = {}
_TOOL_DESCRIPTIONS = {}
def register_tool(func: callable):
tool_name = func.__name__
tool_description = inspect.getdoc(func).strip()
python_params = inspect.signature(func).parameters
tool_params = []
for name, param in python_params.items():
annotation = param.annotation
if annotation is inspect.Parameter.empty:
raise TypeError(f"Parameter `{name}` missing type annotation")
if get_origin(annotation) != Annotated:
raise TypeError(f"Annotation type for `{name}` must be typing.Annotated")
typ, (description, required) = annotation.__origin__, annotation.__metadata__
typ: str = str(typ) if isinstance(typ, GenericAlias) else typ.__name__
if not isinstance(description, str):
raise TypeError(f"Description for `{name}` must be a string")
if not isinstance(required, bool):
raise TypeError(f"Required for `{name}` must be a bool")
tool_params.append({
"name": name,
"description": description,
"type": typ,
"required": required
})
tool_def = {
"name": tool_name,
"description": tool_description,
"params": tool_params
}
print("[registered tool] " + pformat(tool_def))
_TOOL_HOOKS[tool_name] = func
_TOOL_DESCRIPTIONS[tool_name] = tool_def
return func
def dispatch_tool(tool_name: str, tool_params: dict) -> str:
if tool_name not in _TOOL_HOOKS:
return f"Tool `{tool_name}` not found. Please use a provided tool."
tool_call = _TOOL_HOOKS[tool_name]
try:
ret = tool_call(**tool_params)
except:
ret = traceback.format_exc()
return str(ret)
def get_tools() -> dict:
return deepcopy(_TOOL_DESCRIPTIONS)
# Tool Definitions
@register_tool
def random_number_generator(
seed: Annotated[int, 'The random seed used by the generator', True],
range: Annotated[tuple[int, int], 'The range of the generated numbers', True],
) -> int:
"""
Generates a random number x, s.t. range[0] <= x < range[1]
"""
if not isinstance(seed, int):
raise TypeError("Seed must be an integer")
if not isinstance(range, tuple):
raise TypeError("Range must be a tuple")
if not isinstance(range[0], int) or not isinstance(range[1], int):
raise TypeError("Range must be a tuple of integers")
import random
return random.Random(seed).randint(*range)
@register_tool
def get_weather(
city_name: Annotated[str, 'The name of the city to be queried', True],
) -> str:
"""
Get the current weather for `city_name`
"""
if not isinstance(city_name, str):
raise TypeError("City name must be a string")
key_selection = {
"current_condition": ["temp_C", "FeelsLikeC", "humidity", "weatherDesc", "observation_time"],
}
import requests
try:
resp = requests.get(f"https://wttr.in/{city_name}?format=j1")
resp.raise_for_status()
resp = resp.json()
ret = {k: {_v: resp[k][0][_v] for _v in v} for k, v in key_selection.items()}
except:
import traceback
ret = "Error encountered while fetching weather data!\n" + traceback.format_exc()
return str(ret)
if __name__ == "__main__":
print(dispatch_tool("get_weather", {"city_name": "beijing"}))
print(get_tools())
update_requirements.sh 0 → 100644
View file @ dfe42ac1
#!/bin/bash
python -m pip install --upgrade pip -i https://pypi.tuna.tsinghua.edu.cn/simple
while read requirement; do
python -m pip install --upgrade "$requirement" -i https://pypi.tuna.tsinghua.edu.cn/simple
done < requirements.txt
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment