Skip to main content
Open In ColabOpen on GitHub

本地运行模型

用例​

像llama.cpp、Ollama、GPT4All、llamafile等项目的流行，凸显了在本地（在您自己的设备上）运行LLM的需求。

这至少有两个重要的好处：

  1. 隐私: 您的数据不会发送给第三方，也不受商业服务条款的约束
  2. Cost: 没有推理费用，这对于令牌密集型应用程序非常重要（例如，长时间运行的模拟，摘要）

概述​

在本地运行LLM需要几样东西：

  1. Open-source LLM: 一个可以自由修改和共享的开源LLM
  2. Inference: 能够在您的设备上以可接受的延迟运行此LLM

开源LLMs​

用户现在可以访问一个快速增长的开源LLMs集合。

这些LLMs可以在至少两个维度上进行评估（见图）：

  1. Base model: 什么是基础模型以及它是如何训练的？
  2. Fine-tuning approach: 基础模型是否进行了微调，如果是，使用了什么指令集？

图片描述

这些模型的相对性能可以通过几个排行榜来评估，包括：

  1. LmSys
  2. GPT4All
  3. HuggingFace

推理​

已经出现了一些框架来支持在各种设备上对开源LLMs进行推理：

  1. llama.cpp: C++实现的llama推理代码，带有权重优化/量化
  2. gpt4all: 优化的C后端用于推理
  3. Ollama: 将模型权重和环境打包成一个应用程序，该应用程序在设备上运行并提供LLM服务
  4. llamafile: 将模型权重和运行模型所需的所有内容打包到一个文件中，允许您从该文件本地运行LLM，无需任何额外的安装步骤

一般来说，这些框架会做几件事：

  1. Quantization: 减少原始模型权重的内存占用
  2. Efficient implementation for inference: 支持在消费级硬件上进行推理（例如，CPU或笔记本电脑GPU）

特别是，请参阅这篇优秀的文章，了解量化的重要性。

图片描述

通过降低精度，我们大幅减少了在内存中存储LLM所需的内存。

此外，我们可以看到GPU内存带宽的重要性sheet！

由于更大的GPU内存带宽，Mac M2 Max在推理速度上比M1快5-6倍。

图片描述

格式化提示​

一些提供商提供了聊天模型包装器，这些包装器会为你使用的特定本地模型处理输入提示的格式化。然而，如果你使用文本输入/文本输出 LLM包装器来提示本地模型，你可能需要使用针对你特定模型定制的提示。

这可能需要包含特殊标记。这是LLaMA 2的一个示例。

快速开始​

Ollama 是一种在 macOS 上轻松运行推理的方法。

这里的说明提供了详细信息，我们总结如下：

  • Download and run 下载并运行应用程序
  • 从命令行中，从选项列表中获取一个模型：例如，ollama pull llama3.1:8b
  • 当应用程序运行时，所有模型都会自动在 localhost:11434 上提供服务
%pip install -qU langchain_ollama
from langchain_ollama import OllamaLLM

llm = OllamaLLM(model="llama3.1:8b")

llm.invoke("The first man on the moon was ...")
API Reference:OllamaLLM
'...Neil Armstrong!\n\nOn July 20, 1969, Neil Armstrong became the first person to set foot on the lunar surface, famously declaring "That\'s one small step for man, one giant leap for mankind" as he stepped off the lunar module Eagle onto the Moon\'s surface.\n\nWould you like to know more about the Apollo 11 mission or Neil Armstrong\'s achievements?'

在生成时流式传输令牌：

for chunk in llm.stream("The first man on the moon was ..."):
    print(chunk, end="|", flush=True)
...|
``````output
Neil| Armstrong|,| an| American| astronaut|.| He| stepped| out| of| the| lunar| module| Eagle| and| onto| the| surface| of| the| Moon| on| July| |20|,| |196|9|,| famously| declaring|:| "|That|'s| one| small| step| for| man|,| one| giant| leap| for| mankind|."||

Ollama 还包括一个聊天模型包装器，用于处理对话轮次的格式化：

from langchain_ollama import ChatOllama

chat_model = ChatOllama(model="llama3.1:8b")

chat_model.invoke("Who was the first man on the moon?")
API Reference:ChatOllama
AIMessage(content='The answer is a historic one!\n\nThe first man to walk on the Moon was Neil Armstrong, an American astronaut and commander of the Apollo 11 mission. On July 20, 1969, Armstrong stepped out of the lunar module Eagle onto the surface of the Moon, famously declaring:\n\n"That\'s one small step for man, one giant leap for mankind."\n\nArmstrong was followed by fellow astronaut Edwin "Buzz" Aldrin, who also walked on the Moon during the mission. Michael Collins remained in orbit around the Moon in the command module Columbia.\n\nNeil Armstrong passed away on August 25, 2012, but his legacy as a pioneering astronaut and engineer continues to inspire people around the world!', response_metadata={'model': 'llama3.1:8b', 'created_at': '2024-08-01T00:38:29.176717Z', 'message': {'role': 'assistant', 'content': ''}, 'done_reason': 'stop', 'done': True, 'total_duration': 10681861417, 'load_duration': 34270292, 'prompt_eval_count': 19, 'prompt_eval_duration': 6209448000, 'eval_count': 141, 'eval_duration': 4432022000}, id='run-7bed57c5-7f54-4092-912c-ae49073dcd48-0', usage_metadata={'input_tokens': 19, 'output_tokens': 141, 'total_tokens': 160})

环境​

在本地运行模型时，推理速度是一个挑战（见上文）。

为了最小化延迟，最好在本地GPU上运行模型，许多消费级笔记本电脑都配备了GPU，例如苹果设备。

即使使用GPU，可用的GPU内存带宽（如上所述）也很重要。

运行 Apple silicon GPU​

Ollama 和 llamafile 将自动在苹果设备上使用GPU。

其他框架要求用户设置环境以利用Apple GPU。

例如，llama.cpp 的 Python 绑定可以通过 Metal 配置为使用 GPU。

Metal 是苹果公司创建的图形和计算 API，提供近乎直接的 GPU 访问。

请参阅llama.cpp设置这里以启用此功能。

特别是，确保 conda 正在使用你创建的正确虚拟环境 (miniforge3)。

例如，对我来说：

conda activate /Users/rlm/miniforge3/envs/llama

在确认上述内容后，那么：

CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install -U llama-cpp-python --no-cache-dir

大型语言模型​

有多种方法可以获取量化模型权重。

  1. HuggingFace - 许多量化模型可供下载，并且可以使用诸如llama.cpp等框架运行。你也可以从HuggingFace下载llamafile格式的模型。
  2. gpt4all - 模型探索器提供了一个指标排行榜和可供下载的相关量化模型
  3. Ollama - 可以通过pull直接访问多个模型

Ollama​

使用 Ollama，通过 ollama pull : 获取模型：

  • 例如，对于Llama 2 7b：ollama pull llama2 将下载模型的最基本版本（例如，最小的参数数量和4位量化）
  • 我们也可以从模型列表中指定一个特定版本，例如ollama pull llama2:13b
  • 查看完整的参数集，请访问API参考页面
llm = OllamaLLM(model="llama2:13b")
llm.invoke("The first man on the moon was ... think step by step")
' Sure! Here\'s the answer, broken down step by step:\n\nThe first man on the moon was... Neil Armstrong.\n\nHere\'s how I arrived at that answer:\n\n1. The first manned mission to land on the moon was Apollo 11.\n2. The mission included three astronauts: Neil Armstrong, Edwin "Buzz" Aldrin, and Michael Collins.\n3. Neil Armstrong was the mission commander and the first person to set foot on the moon.\n4. On July 20, 1969, Armstrong stepped out of the lunar module Eagle and onto the moon\'s surface, famously declaring "That\'s one small step for man, one giant leap for mankind."\n\nSo, the first man on the moon was Neil Armstrong!'

Llama.cpp​

Llama.cpp 兼容 广泛的模型。

例如，下面我们对从HuggingFace下载的4位量化的llama2-13b进行推理。

如上所述，请参阅API参考以获取完整的参数集。

从llama.cpp API 参考文档中，有几个值得评论的地方：

n_gpu_layers: 加载到GPU内存中的层数

  • 值: 1
  • 含义：只有模型的一层会被加载到GPU内存中（通常1层就足够了）。

n_batch: 模型应并行处理的令牌数量

  • 值：n_batch
  • 含义：建议选择一个介于1和n_ctx之间的值（在这种情况下，n_ctx设置为2048）

n_ctx: 令牌上下文窗口

  • 值: 2048
  • 含义：模型将一次考虑2048个标记的窗口

f16_kv: 模型是否应该对键/值缓存使用半精度

  • 值: 真
  • 含义：模型将使用半精度，这样可以更节省内存；Metal 仅支持 True。
%env CMAKE_ARGS="-DLLAMA_METAL=on"
%env FORCE_CMAKE=1
%pip install --upgrade --quiet  llama-cpp-python --no-cache-dirclear
from langchain_community.llms import LlamaCpp
from langchain_core.callbacks import CallbackManager, StreamingStdOutCallbackHandler

llm = LlamaCpp(
    model_path="/Users/rlm/Desktop/Code/llama.cpp/models/openorca-platypus2-13b.gguf.q4_0.bin",
    n_gpu_layers=1,
    n_batch=512,
    n_ctx=2048,
    f16_kv=True,
    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),
    verbose=True,
)

控制台日志将显示以下内容，以表明从上述步骤中已正确启用Metal：

ggml_metal_init: allocating
ggml_metal_init: using MPS
llm.invoke("The first man on the moon was ... Let's think step by step")
Llama.generate: prefix-match hit
``````output
 and use logical reasoning to figure out who the first man on the moon was.

Here are some clues:

1. The first man on the moon was an American.
2. He was part of the Apollo 11 mission.
3. He stepped out of the lunar module and became the first person to set foot on the moon's surface.
4. His last name is Armstrong.

Now, let's use our reasoning skills to figure out who the first man on the moon was. Based on clue #1, we know that the first man on the moon was an American. Clue #2 tells us that he was part of the Apollo 11 mission. Clue #3 reveals that he was the first person to set foot on the moon's surface. And finally, clue #4 gives us his last name: Armstrong.
Therefore, the first man on the moon was Neil Armstrong!
``````output

llama_print_timings:        load time =  9623.21 ms
llama_print_timings:      sample time =   143.77 ms /   203 runs   (    0.71 ms per token,  1412.01 tokens per second)
llama_print_timings: prompt eval time =   485.94 ms /     7 tokens (   69.42 ms per token,    14.40 tokens per second)
llama_print_timings:        eval time =  6385.16 ms /   202 runs   (   31.61 ms per token,    31.64 tokens per second)
llama_print_timings:       total time =  7279.28 ms
" and use logical reasoning to figure out who the first man on the moon was.\n\nHere are some clues:\n\n1. The first man on the moon was an American.\n2. He was part of the Apollo 11 mission.\n3. He stepped out of the lunar module and became the first person to set foot on the moon's surface.\n4. His last name is Armstrong.\n\nNow, let's use our reasoning skills to figure out who the first man on the moon was. Based on clue #1, we know that the first man on the moon was an American. Clue #2 tells us that he was part of the Apollo 11 mission. Clue #3 reveals that he was the first person to set foot on the moon's surface. And finally, clue #4 gives us his last name: Armstrong.\nTherefore, the first man on the moon was Neil Armstrong!"

GPT4All​

我们可以使用从GPT4All模型浏览器下载的模型权重。

类似于上面所示的内容，我们可以运行推理并使用API参考来设置感兴趣的参数。

%pip install gpt4all
from langchain_community.llms import GPT4All

llm = GPT4All(
    model="/Users/rlm/Desktop/Code/gpt4all/models/nous-hermes-13b.ggmlv3.q4_0.bin"
)
API Reference:GPT4All
llm.invoke("The first man on the moon was ... Let's think step by step")
".\n1) The United States decides to send a manned mission to the moon.2) They choose their best astronauts and train them for this specific mission.3) They build a spacecraft that can take humans to the moon, called the Lunar Module (LM).4) They also create a larger spacecraft, called the Saturn V rocket, which will launch both the LM and the Command Service Module (CSM), which will carry the astronauts into orbit.5) The mission is planned down to the smallest detail: from the trajectory of the rockets to the exact movements of the astronauts during their moon landing.6) On July 16, 1969, the Saturn V rocket launches from Kennedy Space Center in Florida, carrying the Apollo 11 mission crew into space.7) After one and a half orbits around the Earth, the LM separates from the CSM and begins its descent to the moon's surface.8) On July 20, 1969, at 2:56 pm EDT (GMT-4), Neil Armstrong becomes the first man on the moon. He speaks these"

llamafile​

在本地运行LLM的最简单方法之一是使用llamafile。你需要做的就是：

  1. 从HuggingFace下载一个llamafile
  2. 使文件可执行
  3. 运行文件

llamafiles 将模型权重和一个特别编译版本的llama.cpp打包成一个可以在大多数计算机上运行的文件，无需额外的依赖。它们还附带一个嵌入式推理服务器，该服务器提供了一个API用于与您的模型进行交互。

这是一个简单的bash脚本，展示了所有3个设置步骤：

# Download a llamafile from HuggingFace
wget https://huggingface.co/jartine/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile

# Make the file executable. On Windows, instead just rename the file to end in ".exe".
chmod +x TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile

# Start the model server. Listens at http://localhost:8080 by default.
./TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile --server --nobrowser

在您运行上述设置步骤后，您可以使用LangChain与您的模型进行交互：

from langchain_community.llms.llamafile import Llamafile

llm = Llamafile()

llm.invoke("The first man on the moon was ... Let's think step by step.")
API Reference:Llamafile
"\nFirstly, let's imagine the scene where Neil Armstrong stepped onto the moon. This happened in 1969. The first man on the moon was Neil Armstrong. We already know that.\n2nd, let's take a step back. Neil Armstrong didn't have any special powers. He had to land his spacecraft safely on the moon without injuring anyone or causing any damage. If he failed to do this, he would have been killed along with all those people who were on board the spacecraft.\n3rd, let's imagine that Neil Armstrong successfully landed his spacecraft on the moon and made it back to Earth safely. The next step was for him to be hailed as a hero by his people back home. It took years before Neil Armstrong became an American hero.\n4th, let's take another step back. Let's imagine that Neil Armstrong wasn't hailed as a hero, and instead, he was just forgotten. This happened in the 1970s. Neil Armstrong wasn't recognized for his remarkable achievement on the moon until after he died.\n5th, let's take another step back. Let's imagine that Neil Armstrong didn't die in the 1970s and instead, lived to be a hundred years old. This happened in 2036. In the year 2036, Neil Armstrong would have been a centenarian.\nNow, let's think about the present. Neil Armstrong is still alive. He turned 95 years old on July 20th, 2018. If he were to die now, his achievement of becoming the first human being to set foot on the moon would remain an unforgettable moment in history.\nI hope this helps you understand the significance and importance of Neil Armstrong's achievement on the moon!"

提示​

一些LLMs将从特定的提示中受益。

例如，LLaMA 将使用 特殊标记。

我们可以使用ConditionalPromptSelector根据模型类型设置提示。

# Set our LLM
llm = LlamaCpp(
    model_path="/Users/rlm/Desktop/Code/llama.cpp/models/openorca-platypus2-13b.gguf.q4_0.bin",
    n_gpu_layers=1,
    n_batch=512,
    n_ctx=2048,
    f16_kv=True,
    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),
    verbose=True,
)

根据模型版本设置相关的提示。

from langchain.chains.prompt_selector import ConditionalPromptSelector
from langchain_core.prompts import PromptTemplate

DEFAULT_LLAMA_SEARCH_PROMPT = PromptTemplate(
    input_variables=["question"],
    template="""<<SYS>> \n You are an assistant tasked with improving Google search \
results. \n <</SYS>> \n\n [INST] Generate THREE Google search queries that \
are similar to this question. The output should be a numbered list of questions \
and each should have a question mark at the end: \n\n {question} [/INST]""",
)

DEFAULT_SEARCH_PROMPT = PromptTemplate(
    input_variables=["question"],
    template="""You are an assistant tasked with improving Google search \
results. Generate THREE Google search queries that are similar to \
this question. The output should be a numbered list of questions and each \
should have a question mark at the end: {question}""",
)

QUESTION_PROMPT_SELECTOR = ConditionalPromptSelector(
    default_prompt=DEFAULT_SEARCH_PROMPT,
    conditionals=[(lambda llm: isinstance(llm, LlamaCpp), DEFAULT_LLAMA_SEARCH_PROMPT)],
)

prompt = QUESTION_PROMPT_SELECTOR.get_prompt(llm)
prompt
PromptTemplate(input_variables=['question'], output_parser=None, partial_variables={}, template='<<SYS>> \n You are an assistant tasked with improving Google search results. \n <</SYS>> \n\n [INST] Generate THREE Google search queries that are similar to this question. The output should be a numbered list of questions and each should have a question mark at the end: \n\n {question} [/INST]', template_format='f-string', validate_template=True)
# Chain
chain = prompt | llm
question = "What NFL team won the Super Bowl in the year that Justin Bieber was born?"
chain.invoke({"question": question})
  Sure! Here are three similar search queries with a question mark at the end:

1. Which NBA team did LeBron James lead to a championship in the year he was drafted?
2. Who won the Grammy Awards for Best New Artist and Best Female Pop Vocal Performance in the same year that Lady Gaga was born?
3. What MLB team did Babe Ruth play for when he hit 60 home runs in a single season?
``````output

llama_print_timings:        load time = 14943.19 ms
llama_print_timings:      sample time =    72.93 ms /   101 runs   (    0.72 ms per token,  1384.87 tokens per second)
llama_print_timings: prompt eval time = 14942.95 ms /    93 tokens (  160.68 ms per token,     6.22 tokens per second)
llama_print_timings:        eval time =  3430.85 ms /   100 runs   (   34.31 ms per token,    29.15 tokens per second)
llama_print_timings:       total time = 18578.26 ms
'  Sure! Here are three similar search queries with a question mark at the end:\n\n1. Which NBA team did LeBron James lead to a championship in the year he was drafted?\n2. Who won the Grammy Awards for Best New Artist and Best Female Pop Vocal Performance in the same year that Lady Gaga was born?\n3. What MLB team did Babe Ruth play for when he hit 60 home runs in a single season?'

我们也可以使用LangChain Prompt Hub来获取和/或存储特定于模型的提示。

这将与您的LangSmith API key一起使用。

例如，这里是一个带有LLaMA特定标记的RAG提示。

使用案例​

给定一个从上述模型创建的llm，你可以将其用于许多用例。

例如，您可以使用这里展示的聊天模型实现一个RAG应用程序。

一般来说，本地LLM的使用案例至少可以由两个因素驱动：

  • Privacy: 用户不希望分享的私人数据（例如，日记等）
  • Cost: 文本预处理（提取/标记）、摘要和代理模拟是消耗大量token的任务

此外，这里是关于微调的概述，可以利用开源的LLMs。

这个页面有帮助吗？