RELLM

RELLM 是一个库，它包装了用于结构化解码的本地 Hugging Face 管道模型。

它的工作原理是逐个生成标记。在每个步骤中，它都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，让我们通过检查模型在没有结构化解码情况下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，现在提供一个与 JSON 结构化格式匹配的正则表达式。

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