梯度
Gradient 允许使用简单的网络 API 微调 LLM 并获取补全。
此笔记本介绍了如何将 Langchain 与 Gradient 一起使用。
导入
from langchain.chains import LLMChain
from langchain_community.llms import GradientLLM
from langchain_core.prompts import PromptTemplate
设置环境 API 密钥
确保从 Gradient AI 获取您的 API 密钥。您可以获得 10 美元的免费积分来测试和微调不同的模型。
import os
from getpass import getpass
if not os.environ.get("GRADIENT_ACCESS_TOKEN", None):
# Access token under https://auth.gradient.ai/select-workspace
os.environ["GRADIENT_ACCESS_TOKEN"] = getpass("gradient.ai access token:")
if not os.environ.get("GRADIENT_WORKSPACE_ID", None):
# `ID` listed in `$ gradient workspace list`
# also displayed after login at at https://auth.gradient.ai/select-workspace
os.environ["GRADIENT_WORKSPACE_ID"] = getpass("gradient.ai workspace id:")
可选：验证您的环境变量 GRADIENT_ACCESS_TOKEN 和 GRADIENT_WORKSPACE_ID 以获取当前部署的模型。使用 gradientai Python 包。
%pip install --upgrade --quiet gradientai
Requirement already satisfied: gradientai in /home/michi/.venv/lib/python3.10/site-packages (1.0.0)
Requirement already satisfied: aenum>=3.1.11 in /home/michi/.venv/lib/python3.10/site-packages (from gradientai) (3.1.15)
Requirement already satisfied: pydantic<2.0.0,>=1.10.5 in /home/michi/.venv/lib/python3.10/site-packages (from gradientai) (1.10.12)
Requirement already satisfied: python-dateutil>=2.8.2 in /home/michi/.venv/lib/python3.10/site-packages (from gradientai) (2.8.2)
Requirement already satisfied: urllib3>=1.25.3 in /home/michi/.venv/lib/python3.10/site-packages (from gradientai) (1.26.16)
Requirement already satisfied: typing-extensions>=4.2.0 in /home/michi/.venv/lib/python3.10/site-packages (from pydantic<2.0.0,>=1.10.5->gradientai) (4.5.0)
Requirement already satisfied: six>=1.5 in /home/michi/.venv/lib/python3.10/site-packages (from python-dateutil>=2.8.2->gradientai) (1.16.0)
import gradientai
client = gradientai.Gradient()
models = client.list_models(only_base=True)
for model in models:
print(model.id)
99148c6d-c2a0-4fbe-a4a7-e7c05bdb8a09_base_ml_model
f0b97d96-51a8-4040-8b22-7940ee1fa24e_base_ml_model
cc2dafce-9e6e-4a23-a918-cad6ba89e42e_base_ml_model
new_model = models[-1].create_model_adapter(name="my_model_adapter")
new_model.id, new_model.name
('674119b5-f19e-4856-add2-767ae7f7d7ef_model_adapter', 'my_model_adapter')
创建 Gradient 实例
您可以指定不同的参数，例如模型、生成的 max_tokens、温度等。
由于我们稍后希望微调我们的模型，因此我们选择具有 ID 674119b5-f19e-4856-add2-767ae7f7d7ef_model_adapter 的模型适配器，但您可以使用任何基础模型或可微调模型。
llm = GradientLLM(
# `ID` listed in `$ gradient model list`
model="674119b5-f19e-4856-add2-767ae7f7d7ef_model_adapter",
# # optional: set new credentials, they default to environment variables
# gradient_workspace_id=os.environ["GRADIENT_WORKSPACE_ID"],
# gradient_access_token=os.environ["GRADIENT_ACCESS_TOKEN"],
model_kwargs=dict(max_generated_token_count=128),
)
创建提示模板
我们将为问答创建一个提示模板。
template = """Question: {question}
Answer: """
prompt = PromptTemplate.from_template(template)
启动 LLMChain
llm_chain = LLMChain(prompt=prompt, llm=llm)
运行 LLMChain
提供一个问题并运行 LLMChain。
question = "What NFL team won the Super Bowl in 1994?"
llm_chain.run(question=question)
'\nThe San Francisco 49ers won the Super Bowl in 1994.'
通过微调改进结果（可选）
嗯，这是错误的 - 旧金山 49 人队没有获胜。这个问题的正确答案应该是 达拉斯牛仔队！。
让我们通过使用 PromptTemplate 对正确答案进行微调来增加正确答案的几率。
dataset = [
{
"inputs": template.format(question="What NFL team won the Super Bowl in 1994?")
+ " The Dallas Cowboys!"
}
]
dataset
[{'inputs': 'Question: What NFL team won the Super Bowl in 1994?\n\nAnswer: The Dallas Cowboys!'}]
new_model.fine_tune(samples=dataset)
FineTuneResponse(number_of_trainable_tokens=27, sum_loss=78.17996)
# we can keep the llm_chain, as the registered model just got refreshed on the gradient.ai servers.
llm_chain.run(question=question)
'The Dallas Cowboys'