花崗巖3.0

Granite 3.0 是一個開源、輕量級的生成語言模型系列，專為一系列企業(yè)級任務而設計。它原生支持多語言功能、編碼、推理和工具使用，適合企業(yè)環(huán)境。

我測試了運行這個模型，看看它可以處理哪些任務。

環(huán)境設置

我在 Google Colab 中設置了 Granite 3.0 環(huán)境，并使用以下命令安裝了必要的庫：

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

執(zhí)行

我測試了Granite 3.0的2B和8B型號的性能。

2B型號

我運行了 2B 模型。這是 2B 模型的代碼示例：

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])

輸出

<|start_of_role|>user<|end_of_role|>Please list one IBM Research laboratory located in the United States. You should only output its name and location.<|end_of_text|>
<|start_of_role|>assistant<|end_of_role|>1. IBM Research - Austin, Texas<|end_of_text|>

8B型號

將2b替換為8b即可使用8B模型。以下是 8B 模型的沒有角色和用戶輸入字段的代碼示例：

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)

輸出

1. IBM Almaden Research Center - San Jose, California

函數(shù)調用

我探索了函數(shù)調用功能，并使用虛擬函數(shù)對其進行了測試。這里，get_current_weather 被定義為返回模擬天氣數(shù)據(jù)。

虛擬函數(shù)

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"}

即時創(chuàng)作

我創(chuàng)建了一個調用該函數(shù)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 }
]

響應生成

使用以下代碼，我生成了一個響應：

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)

輸出

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

這證實了模型能夠根據(jù)指定城市生成正確的函數(shù)調用。

增強交互流程的格式規(guī)范

Granite 3.0 允許格式規(guī)范以促進結構化格式的響應。本節(jié)解釋如何使用 [UTTERANCE] 進行回應，使用 [THINK] 進行內心想法。

另一方面，由于函數(shù)調用以純文本形式輸出，因此可能需要實現(xiàn)單獨的機制來區(qū)分函數(shù)調用和常規(guī)文本響應。

指定輸出格式

以下是指導 AI 輸出的示例提示：

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

Follow these instructions, alternating between [UTTERANCE] and [THINK] formats for responses.
<output example>
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.
...
</output example>

Please respond to the following user_input.
<user_input>
Hello! What can you do?
</user_input>
"""

執(zhí)行代碼示例

生成響應的代碼：

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)

示例輸出

輸出如下：

[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] 標簽已成功使用，允許有效的響應格式。

根據(jù)提示的不同，輸出中有時可能會出現(xiàn)結束標簽（例如[/UTTERANCE]或[/THINK]），但總的來說，一般都可以成功指定輸出格式。

流式傳輸代碼示例

讓我們看看如何輸出流響應。

以下代碼使用 asyncio 和線程庫來異步傳輸來自 Granite 3.0 的響應。

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

示例輸出

運行上述代碼將生成以下格式的異步響應：

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])

此示例演示了成功的流式傳輸。每個token都是異步生成并順序顯示，讓用戶可以實時查看生成過程。

概括

Granite 3.0 即使使用 8B 型號也能提供相當強的響應。函數(shù)調用和格式規(guī)范功能也運行良好，表明其具有廣泛的應用潛力。

以上是我嘗試過花崗巖。的詳細內容。更多信息請關注PHP中文網其他相關文章！