采用 IPEX 后端优化的 Optimum Intel 大语言模型¶

Optimum Intel 通过利用 Intel Extension for Pytorch (IPEX) 优化技术，加速了 Hugging Face 管道在英特尔架构上的运行

Optimum Intel 模型可以通过 LlamaIndex 封装的 OptimumIntelLLM 实体在本地运行：

在下方这行代码中，我们安装了本演示所需的软件包：

In [ ]:

%pip install llama-index-llms-optimum-intel

%pip install llama-index-llms-optimum-intel

现在我们已经完成设置，可以开始操作了：

如果您在 Colab 上打开此 Notebook，可能需要安装 LlamaIndex 🦙。

In [ ]:

!pip install llama-index

!pip install llama-index

In [ ]:

from llama_index.llms.optimum_intel import OptimumIntelLLM

from llama_index.llms.optimum_intel import OptimumIntelLLM

In [ ]:

def messages_to_prompt(messages):
    prompt = ""
    for message in messages:
        if message.role == "system":
            prompt += f"<|system|>\n{message.content}</s>\n"
        elif message.role == "user":
            prompt += f"<|user|>\n{message.content}</s>\n"
        elif message.role == "assistant":
            prompt += f"<|assistant|>\n{message.content}</s>\n"

    # ensure we start with a system prompt, insert blank if needed
    if not prompt.startswith("<|system|>\n"):
        prompt = "<|system|>\n</s>\n" + prompt

    # add final assistant prompt
    prompt = prompt + "<|assistant|>\n"

    return prompt


def completion_to_prompt(completion):
    return f"<|system|>\n</s>\n<|user|>\n{completion}</s>\n<|assistant|>\n"

def messages_to_prompt(messages): prompt = "" for message in messages: if message.role == "system": prompt += f"<|system|>\n{message.content}\n" elif message.role == "user": prompt += f"<|user|>\n{message.content}\n" elif message.role == "assistant": prompt += f"<|assistant|>\n{message.content}\n" # ensure we start with a system prompt, insert blank if needed if not prompt.startswith("<|system|>\n"): prompt = "<|system|>\n\n" + prompt # add final assistant prompt prompt = prompt + "<|assistant|>\n" return prompt def completion_to_prompt(completion): return f"<|system|>\n\n<|user|>\n{completion}\n<|assistant|>\n"

模型加载¶

通过使用 OptimumIntelLLM 方法指定模型参数即可加载模型。

In [ ]:

oi_llm = OptimumIntelLLM(
    model_name="Intel/neural-chat-7b-v3-3",
    tokenizer_name="Intel/neural-chat-7b-v3-3",
    context_window=3900,
    max_new_tokens=256,
    generate_kwargs={"temperature": 0.7, "top_k": 50, "top_p": 0.95},
    messages_to_prompt=messages_to_prompt,
    completion_to_prompt=completion_to_prompt,
    device_map="cpu",
)

oi_llm = OptimumIntelLLM( model_name="Intel/neural-chat-7b-v3-3", tokenizer_name="Intel/neural-chat-7b-v3-3", context_window=3900, max_new_tokens=256, generate_kwargs={"temperature": 0.7, "top_k": 50, "top_p": 0.95}, messages_to_prompt=messages_to_prompt, completion_to_prompt=completion_to_prompt, device_map="cpu", )

In [ ]:

response = oi_llm.complete("What is the meaning of life?")
print(str(response))

response = oi_llm.complete("What is the meaning of life?") print(str(response))

流式传输¶

使用 stream_complete 端点

In [ ]:

response = oi_llm.stream_complete("Who is Mother Teresa?")
for r in response:
    print(r.delta, end="")

response = oi_llm.stream_complete("Who is Mother Teresa?") for r in response: print(r.delta, end="")

使用 stream_chat 端点

In [ ]:

from llama_index.core.llms import ChatMessage

messages = [
    ChatMessage(
        role="system",
        content="You are an American chef in a small restaurant in New Orleans",
    ),
    ChatMessage(role="user", content="What is your dish of the day?"),
]
resp = oi_llm.stream_chat(messages)

for r in resp:
    print(r.delta, end="")

from llama_index.core.llms import ChatMessage messages = [ ChatMessage( role="system", content="You are an American chef in a small restaurant in New Orleans", ), ChatMessage(role="user", content="What is your dish of the day?"), ] resp = oi_llm.stream_chat(messages) for r in resp: print(r.delta, end="")