RELLM

RELLM 是一个库，它为结构化解码封装了本地 Hugging Face 管道模型。

它通过一次生成一个标记来工作。在每一步中，它会屏蔽不符合提供的部分正则表达式的标记。

警告 - 此模块仍在实验阶段

%pip install --upgrade --quiet  rellm langchain-huggingface > /dev/null

Hugging Face 基线

首先，让我们通过检查没有结构化解码的模型的输出，建立一个定性基线。

import logging

logging.basicConfig(level=logging.ERROR)
prompt = """Human: "What's the capital of the United States?"
AI Assistant:{
  "action": "Final Answer",
  "action_input": "The capital of the United States is Washington D.C."
}
Human: "What's the capital of Pennsylvania?"
AI Assistant:{
  "action": "Final Answer",
  "action_input": "The capital of Pennsylvania is Harrisburg."
}
Human: "What 2 + 5?"
AI Assistant:{
  "action": "Final Answer",
  "action_input": "2 + 5 = 7."
}
Human: 'What's the capital of Maryland?'
AI Assistant:"""

from langchain_huggingface import HuggingFacePipeline
from transformers import pipeline

hf_model = pipeline(
    "text-generation", model="cerebras/Cerebras-GPT-590M", max_new_tokens=200
)

original_model = HuggingFacePipeline(pipeline=hf_model)

generated = original_model.generate([prompt], stop=["Human:"])
print(generated)

API 参考：HuggingFacePipeline

Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.
``````output
generations=[[Generation(text=' "What\'s the capital of Maryland?"\n', generation_info=None)]] llm_output=None

这并不令人印象深刻，是吗？它没有回答问题，也没有遵循 JSON 格式！让我们尝试使用结构化解码器。

RELLM LLM 包装器

让我们再试一次，现在提供一个正则表达式来匹配 JSON 结构化格式。

import regex  # Note this is the regex library NOT python's re stdlib module

# We'll choose a regex that matches to a structured json string that looks like:
# {
#  "action": "Final Answer",
# "action_input": string or dict
# }
pattern = regex.compile(
    r'\{\s*"action":\s*"Final Answer",\s*"action_input":\s*(\{.*\}|"[^"]*")\s*\}\nHuman:'
)

from langchain_experimental.llms import RELLM

model = RELLM(pipeline=hf_model, regex=pattern, max_new_tokens=200)

generated = model.predict(prompt, stop=["Human:"])
print(generated)

API 参考：RELLM

{"action": "Final Answer",
  "action_input": "The capital of Maryland is Baltimore."
}

瞧！没有解析错误。

相关

• LLM 概念指南
• LLM 操作指南