Skip to main content
本 notebook 展示如何通过 Llama2Chat 封装器来增强 Llama-2 LLM，以支持 Llama-2 聊天提示格式。LangChain 中的多个 LLM 实现可用作 Llama-2 聊天模型的接口，例如 ChatHuggingFace、LlamaCpp、GPT4All 等。 Llama2Chat 是一个通用封装器，实现了 BaseChatModel，因此可以在应用程序中作为聊天模型使用。Llama2Chat 将消息列表转换为所需的聊天提示格式，并将格式化后的提示以 str 形式转发给封装的 LLM。 
from langchain_classic.chains import LLMChain
from langchain.memory import ConversationBufferMemory
from langchain_experimental.chat_models import Llama2Chat
在以下聊天应用示例中，我们将使用如下聊天 prompt_template： 
from langchain.messages import SystemMessage
from langchain_core.prompts.chat import (
    ChatPromptTemplate,
    HumanMessagePromptTemplate,
    MessagesPlaceholder,
)

template_messages = [
    SystemMessage(content="You are a helpful assistant."),
    MessagesPlaceholder(variable_name="chat_history"),
    HumanMessagePromptTemplate.from_template("{text}"),
]
prompt_template = ChatPromptTemplate.from_messages(template_messages)

​
通过 HuggingFaceTextGenInference LLM 与 Llama-2 聊天

HuggingFaceTextGenInference LLM 封装了对 text-generation-inference 服务器的访问。在以下示例中，推理服务器提供 meta-llama/Llama-2-13b-chat-hf 模型。可以使用如下命令在本地启动： 
docker run \
  --rm \
  --gpus all \
  --ipc=host \
  -p 8080:80 \
  -v ~/.cache/huggingface/hub:/data \
  -e HF_API_TOKEN=${HF_API_TOKEN} \
  ghcr.io/huggingface/text-generation-inference:0.9 \
  --hostname 0.0.0.0 \
  --model-id meta-llama/Llama-2-13b-chat-hf \
  --quantize bitsandbytes \
  --num-shard 4
此示例在配备 4 块 RTX 3080ti 显卡的机器上运行。请根据可用 GPU 数量调整 --num_shard 值。HF_API_TOKEN 环境变量存放 Hugging Face API 令牌。 
# !pip3 install text-generation
创建连接到本地推理服务器的 HuggingFaceTextGenInference 实例，并将其封装到 Llama2Chat 中。 
from langchain_community.llms import HuggingFaceTextGenInference

llm = HuggingFaceTextGenInference(
    inference_server_url="http://127.0.0.1:8080/",
    max_new_tokens=512,
    top_k=50,
    temperature=0.1,
    repetition_penalty=1.03,
)

model = Llama2Chat(llm=llm)
然后，您就可以在 LLMChain 中将聊天 model 与 prompt_template 及对话 memory 结合使用了。 
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
chain = LLMChain(llm=model, prompt=prompt_template, memory=memory)

print(
    chain.run(
        text="What can I see in Vienna? Propose a few locations. Names only, no details."
    )
)

 Sure, I'd be happy to help! Here are a few popular locations to consider visiting in Vienna:

1. Schönbrunn Palace
2. St. Stephen's Cathedral
3. Hofburg Palace
4. Belvedere Palace
5. Prater Park
6. Vienna State Opera
7. Albertina Museum
8. Museum of Natural History
9. Kunsthistorisches Museum
10. Ringstrasse

print(chain.run(text="Tell me more about #2."))

 Certainly! St. Stephen's Cathedral (Stephansdom) is one of the most recognizable landmarks in Vienna and a must-see attraction for visitors. This stunning Gothic cathedral is located in the heart of the city and is known for its intricate stone carvings, colorful stained glass windows, and impressive dome.

The cathedral was built in the 12th century and has been the site of many important events throughout history, including the coronation of Holy Roman emperors and the funeral of Mozart. Today, it is still an active place of worship and offers guided tours, concerts, and special events. Visitors can climb up the south tower for panoramic views of the city or attend a service to experience the beautiful music and chanting.

​
通过 LlamaCPP LLM 与 Llama-2 聊天

要通过 LlamaCPP LMM 使用 Llama-2 聊天模型，请按照安装说明安装 llama-cpp-python 库。以下示例使用存储在本地 ~/Models/llama-2-7b-chat.Q4_0.gguf 路径下的量化 llama-2-7b-chat.Q4_0.gguf 模型。 创建 LlamaCpp 实例后，再次将 llm 封装到 Llama2Chat 中： 
from os.path import expanduser

from langchain_community.llms import LlamaCpp

model_path = expanduser("~/Models/llama-2-7b-chat.Q4_0.gguf")

llm = LlamaCpp(
    model_path=model_path,
    streaming=False,
)
model = Llama2Chat(llm=llm)
使用方式与前面的示例相同。 
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
chain = LLMChain(llm=model, prompt=prompt_template, memory=memory)

print(
    chain.run(
        text="What can I see in Vienna? Propose a few locations. Names only, no details."
    )
)

  Of course! Vienna is a beautiful city with a rich history and culture. Here are some of the top tourist attractions you might want to consider visiting:
1. Schönbrunn Palace
2. St. Stephen's Cathedral
3. Hofburg Palace
4. Belvedere Palace
5. Prater Park
6. MuseumsQuartier
7. Ringstrasse
8. Vienna State Opera
9. Kunsthistorisches Museum
10. Imperial Palace

These are just a few of the many amazing places to see in Vienna. Each one has its own unique history and charm, so I hope you enjoy exploring this beautiful city!

llama_print_timings:        load time =     250.46 ms
llama_print_timings:      sample time =      56.40 ms /   144 runs   (    0.39 ms per token,  2553.37 tokens per second)
llama_print_timings: prompt eval time =    1444.25 ms /    47 tokens (   30.73 ms per token,    32.54 tokens per second)
llama_print_timings:        eval time =    8832.02 ms /   143 runs   (   61.76 ms per token,    16.19 tokens per second)
llama_print_timings:       total time =   10645.94 ms

print(chain.run(text="Tell me more about #2."))

Llama.generate: prefix-match hit

  Of course! St. Stephen's Cathedral (also known as Stephansdom) is a stunning Gothic-style cathedral located in the heart of Vienna, Austria. It is one of the most recognizable landmarks in the city and is considered a symbol of Vienna.
Here are some interesting facts about St. Stephen's Cathedral:
1. History: The construction of St. Stephen's Cathedral began in the 12th century on the site of a former Romanesque church, and it took over 600 years to complete. The cathedral has been renovated and expanded several times throughout its history, with the most significant renovation taking place in the 19th century.
2. Architecture: St. Stephen's Cathedral is built in the Gothic style, characterized by its tall spires, pointed arches, and intricate stone carvings. The cathedral features a mix of Romanesque, Gothic, and Baroque elements, making it a unique blend of styles.
3. Design: The cathedral's design is based on the plan of a cross with a long nave and two shorter arms extending from it. The main altar is

llama_print_timings:        load time =     250.46 ms
llama_print_timings:      sample time =     100.60 ms /   256 runs   (    0.39 ms per token,  2544.73 tokens per second)
llama_print_timings: prompt eval time =    5128.71 ms /   160 tokens (   32.05 ms per token,    31.20 tokens per second)
llama_print_timings:        eval time =   16193.02 ms /   255 runs   (   63.50 ms per token,    15.75 tokens per second)
llama_print_timings:       total time =   21988.57 ms
在 GitHub 上编辑此页面 或 提交问题。
将这些文档连接到 Claude、VSCode 等，通过 MCP 获取实时解答。