跳到主要内容

使用微调的 gpt-3.5-turbo

LiteLLM 允许你使用微调的 gpt-3.5-turbo 模型调用 completion。如果你正尝试按照此教程创建自定义微调的 gpt-3.5-turbo 模型：https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset

创建你的微调模型后，可以使用 litellm.completion() 调用它

用法​

import os
from litellm import completion

# LiteLLM reads from your .env
os.environ["OPENAI_API_KEY"] = "your-api-key"

response = completion(
  model="ft:gpt-3.5-turbo:my-org:custom_suffix:id",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ]
)

print(response.choices[0].message)

用法 - 设置 OpenAI Organization ID​

调用 OpenAI LLMs 时，LiteLLM 允许你指定你的 OpenAI Organization。更多详情请见此处：设置 Organization ID 可以通过以下方式之一进行设置

  • 环境变量 OPENAI_ORGANIZATION
  • litellm.completion(model=model, organization="your-organization-id") 的参数
  • 设置为 litellm.organization="your-organization-id"
import os
from litellm import completion

# LiteLLM reads from your .env
os.environ["OPENAI_API_KEY"] = "your-api-key"
os.environ["OPENAI_ORGANIZATION"] = "your-org-id" # Optional

response = completion(
  model="ft:gpt-3.5-turbo:my-org:custom_suffix:id",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ]
)

print(response.choices[0].message)