花岗岩3.0

Granite 3.0 是一个开源、轻量级的生成语言模型系列，专为一系列企业级任务而设计。它原生支持多语言功能、编码、推理和工具使用，使其适合企业环境。

我测试了运行这个模型，看看它可以处理哪些任务。

环境设置

我在Google Colab中设置了Granite 3.0环境并使用以下命令安装了必要的库：

!pip install torch torchvision torchaudio
!pip install accelerate
!pip install -U transformers

执行

我测试了Granite 3.0的2B和8B型号的性能。

2B型号

我运行了 2B 模型。这是 2B 模型的代码示例：

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "auto"
model_path = "ibm-granite/granite-3.0-2b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()

chat = [
    { "role": "user", "content": "Please list one IBM Research laboratory located in the United States. You should only output its name and location." },
]
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
input_tokens = tokenizer(chat, return_tensors="pt").to("cuda")
output = model.generate(**input_tokens, max_new_tokens=100)
output = tokenizer.batch_decode(output)
print(output[0])

输出

userPlease list one IBM Research laboratory located in the United States. You should only output its name and location.
assistant1. IBM Research - Austin, Texas

8B型号

将2b替换为8b即可使用8B模型。以下是 8B 模型的没有角色和用户输入字段的代码示例：

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "auto"
model_path = "ibm-granite/granite-3.0-8b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()

chat = [
    { "content": "Please list one IBM Research laboratory located in the United States. You should only output its name and location." },
]
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

input_tokens = tokenizer(chat, add_special_tokens=False, return_tensors="pt").to("cuda")
output = model.generate(**input_tokens, max_new_tokens=100)
generated_text = tokenizer.decode(output[0][input_tokens["input_ids"].shape[1]:], skip_special_tokens=True)
print(generated_text)

输出

1. IBM Almaden Research Center - San Jose, California

函数调用

我探索了函数调用功能，并使用虚拟函数对其进行了测试。这里，get_current_weather被定义为返回模拟天气数据。

虚拟函数

import json

def get_current_weather(location: str) -> dict:
    """
    Retrieves current weather information for the specified location (default: San Francisco).
    Args:
        location (str): Name of the city to retrieve weather data for.
    Returns:
        dict: Dictionary containing weather information (temperature, description, humidity).
    """
    print(f"Getting current weather for {location}")

    try:
        weather_description = "sample"
        temperature = "20.0"
        humidity = "80.0"

        return {
            "description": weather_description,
            "temperature": temperature,
            "humidity": humidity
        }
    except Exception as e:
        print(f"Error fetching weather data: {e}")
        return {"weather": "NA"}

即时创作

我创建了调用该函数的提示：

functions = [
    {
        "name": "get_current_weather",
        "description": "Get the current weather",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and country code, e.g. San Francisco, US",
                }
            },
            "required": ["location"],
        },
    },
]
query = "What's the weather like in Boston?"
payload = {
    "functions_str": [json.dumps(x) for x in functions]
}
chat = [
    {"role":"system","content": f"You are a helpful assistant with access to the following function calls. Your task is to produce a sequence of function calls necessary to generate response to the user utterance. Use the following function calls as required.{payload}"},
    {"role": "user", "content": query }
]

响应生成

使用以下代码，我生成了一个响应：

instruction_1 = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
input_tokens = tokenizer(instruction_1, return_tensors="pt").to("cuda")
output = model.generate(**input_tokens, max_new_tokens=1024)
generated_text = tokenizer.decode(output[0][input_tokens["input_ids"].shape[1]:], skip_special_tokens=True)
print(generated_text)

输出

{'name': 'get_current_weather', 'arguments': {'location': 'Boston'}}

这证实了模型能够根据指定城市生成正确的函数调用。

增强交互流程的格式规范

Granite 3.0 允许格式规范以促进结构化格式的响应。本节解释如何使用 [UTTERANCE] 进行回应，使用 [THINK] 进行内心想法。

另一方面，由于函数调用以纯文本形式输出，因此可能需要实现单独的机制来区分函数调用和常规文本响应。

指定输出格式

以下是指导 AI 输出的示例提示：

prompt = """You are a conversational AI assistant that deepens interactions by alternating between responses and inner thoughts.

* Record spoken responses after the [UTTERANCE] tag and inner thoughts after the [THINK] tag.
* Use [UTTERANCE] as a start marker to begin outputting an utterance.
* After [THINK], describe your internal reasoning or strategy for the next response. This may include insights on the user's reaction, adjustments to improve interaction, or further goals to deepen the conversation.
* Important: **Use [UTTERANCE] and [THINK] as a start signal without needing a closing tag.**


Follow these instructions, alternating between [UTTERANCE] and [THINK] formats for responses.

example1:
  [UTTERANCE]Hello! How can I assist you today?[THINK]I’ll start with a neutral tone to understand their needs. Preparing to offer specific suggestions based on their response.[UTTERANCE]Thank you! In that case, I have a few methods I can suggest![THINK]Since I now know what they’re looking for, I'll move on to specific suggestions, maintaining a friendly and approachable tone.
...
example>

Please respond to the following user_input.

Hello! What can you do?

"""

执行代码示例

生成响应的代码：

chat = [
    { "role": "user", "content": prompt },
]
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

input_tokens = tokenizer(chat, return_tensors="pt").to("cuda")
output = model.generate(**input_tokens, max_new_tokens=1024)
generated_text = tokenizer.decode(output[0][input_tokens["input_ids"].shape[1]:], skip_special_tokens=True)
print(generated_text)

示例输出

输出如下：

[UTTERANCE]Hello! I'm here to provide information, answer questions, and assist with various tasks. I can help with a wide range of topics, from general knowledge to specific queries. How can I assist you today?
[THINK]I've introduced my capabilities and offered assistance, setting the stage for the user to share their needs or ask questions.

[UTTERANCE] 和 [THINK] 标签已成功使用，允许有效的响应格式。

根据提示的不同，输出中有时可能会出现结束标记（例如[/UTTERANCE]或[/THINK]），但总的来说，通常可以成功指定输出格式。

流式传输代码示例

让我们看看如何输出流响应。

以下代码使用 asyncio 和线程库异步传输来自 Granite 3.0 的响应。

import asyncio
from threading import Thread
from typing import AsyncIterator
from transformers import (
    AutoTokenizer,
    AutoModelForCausalLM,
    TextIteratorStreamer,
)

device = "auto"
model_path = "ibm-granite/granite-3.0-8b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()

async def generate(chat) -> AsyncIterator[str]:
    # Apply chat template and tokenize input
    chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
    input_tokens = tokenizer(chat, add_special_tokens=False, return_tensors="pt").to("cuda")

    # Set up the streamer
    streamer = TextIteratorStreamer(
        tokenizer,
        skip_prompt=True,
        skip_special_tokens=True,
    )
    generation_kwargs = dict(
        **input_tokens,
        streamer=streamer,
        max_new_tokens=1024,
    )
    # Generate response in a separate thread
    thread = Thread(target=model.generate, kwargs=generation_kwargs)
    thread.start()

    for output in streamer:
        if not output:
            continue
        await asyncio.sleep(0)
        yield output

# Execute asynchronous generation in the main function
async def main():
    chat = [
        { "role": "user", "content": "Please list one IBM Research laboratory located in the United States. You should only output its name and location." },
    ]
    generator = generate(chat)
    async for output in generator:  # Use async for to retrieve responses sequentially
        print(output, end="|")

await main()

示例输出

运行上述代码将生成以下格式的异步响应：

1. |IBM |Almaden |Research |Center |- |San |Jose, |California|

此示例演示了成功的流式传输。每个token都是异步生成并顺序显示，让用户可以实时查看生成过程。

概括

Granite 3.0 即使使用 8B 型号也能提供相当强的响应。函数调用和格式规范功能也运行良好，表明其具有广泛的应用潜力。