ModelHub XC a96b9fba25 初始化项目,由ModelHub XC社区提供模型
Model: rubraAI/Qwen2-7B-Instruct
Source: Original Platform
2026-06-23 06:58:13 +08:00

license, library_name, pipeline_tag, model-index, tags, language
license library_name pipeline_tag model-index tags language
apache-2.0 transformers text-generation
name results
Rubra-Qwen2-7B-Instruct
task dataset metrics
type
text-generation
type name
MMLU MMLU
type value verified
5-shot 68.88 false
task dataset metrics
type
text-generation
type name
GPQA GPQA
type value verified
0-shot 30.36 false
task dataset metrics
type
text-generation
type name
GSM-8K GSM-8K
type value verified
8-shot, CoT 75.82 false
task dataset metrics
type
text-generation
type name
MATH MATH
type value verified
4-shot, CoT 28.72 false
task dataset metrics
type
text-generation
type name
MT-bench MT-bench
type value verified
GPT-4 as Judge 8.08 false
function-calling
tool-calling
agentic
rubra
conversational
对话
工具调用
量化
en
zh

Qwen2 7B Instruct

Model description

本模型是在进一步微调 Qwen/Qwen2-7B-Instruct 的结果. 它能够进行多轮复杂的工具调用。

Training

本模型在包含多样化工具的调用、聊天数据集和Instruct数据的专有数据集上进行了进一步post-trainingfreeze tuned和DPO

使用方法

您可以使用Hugging Face的transformers和rubra库rubra-tools来使用该模型,如下所示:

pip install rubra_tools torch==2.3.0 transformers accelerate modelscope

您还需要安装Node.js和npm。安装后请安装jsonrepair包 - 用于修复模型的一些罕见错误。

npm install jsonrepair

1. 加载模型

from modelscope import AutoModelForCausalLM, AutoTokenizer
import torch
from rubra_tools import preprocess_input, postprocess_output

model_id = "rubraAI/Meta-Llama-3-8B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

2. 定义函数

这里我们使用4个函数来解决一个简单的数学问题

functions = [
    {
            'type': 'function',
            'function': {
                'name': 'addition',
                'description': "Adds two numbers together",
                'parameters': {
                    'type': 'object',
                    'properties': {
                        'a': {
                            'description': 'First number to add',
                            'type': 'string'
                        },
                        'b': {
                            'description': 'Second number to add',
                            'type': 'string'
                        }
                    },
                    'required': []
                }
            }
        },
        {
            'type': 'function',
            'function': {
                'name': 'subtraction',
                'description': "Subtracts two numbers",
                'parameters': {
                    'type': 'object',
                    'properties': {
                        'a': {
                            'description': 'First number to be subtracted from',
                            'type': 'string'
                        },
                        'b': {
                            'description': 'Number to subtract',
                            'type': 'string'
                        }
                    },
                    'required': []
                }
            }
        },
        {
            'type': 'function',
            'function': {
                'name': 'multiplication',
                'description': "Multiply two numbers together",
                'parameters': {
                    'type': 'object',
                    'properties': {
                        'a': {
                            'description': 'First number to multiply',
                            'type': 'string'
                        },
                        'b': {
                            'description': 'Second number to multiply',
                            'type': 'string'
                        }
                    },
                    'required': []
                }
            }
        },
        {
            'type': 'function',
            'function': {
                'name': 'division',
                'description': "Divide two numbers",
                'parameters': {
                    'type': 'object',
                    'properties': {
                        'a': {
                            'description': 'First number to use as the dividend',
                            'type': 'string'
                        },
                        'b': {
                            'description': 'Second number to use as the divisor',
                            'type': 'string'
                        }
                    },
                    'required': []
                }
            }
        },
]

3. 开始对话

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is the result of four plus six? Take the result and add 2? Then multiply by 5 and then divide by two"},
]

def run_model(messages, functions):
    ## Format messages in Rubra's format
    formatted_msgs = preprocess_input(msgs=messages, tools=functions)

    text = tokenizer.apply_chat_template(
        formatted_msgs,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(
        model_inputs.input_ids,
        max_new_tokens=512
    )
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response

raw_output = run_model(messages, functions)
# Check if there's a function call
function_call = postprocess_output(raw_output)
if function_call:
    print(function_call)
else:
    print(raw_output)

您应该会看到以下输出这是AI助手进行的工具调用

[{'id': 'fc65a533', 'function': {'name': 'addition', 'arguments': '{"a": "4", "b": "6"}'}, 'type': 'function'}]

4. 将执行工具调用的结果添加到消息历史记录并继续对话

if function_call:
    # append the assistant tool call msg
    messages.append({"role": "assistant", "tool_calls": function_call})
    # append the result of the tool call in openai format, in this case, the value of add 6 to 4 is 10.
    messages.append({'role': 'tool', 'tool_call_id': function_call[0]["id"], 'name': function_call[0]["function"]["name"], 'content': '10'})
    raw_output1 = run_model(messages, functions)
    # Check if there's a function call

    function_call = postprocess_output(raw_output1)
    if function_call:
        print(function_call)
    else:
        print(raw_output)

LLM将再次进行调用

[{'id': '2ffc3de4', 'function': {'name': 'addition', 'arguments': '{"a": "10", "b": "2"}'}, 'type': 'function'}]

框架版本

  • Transformers 4.41.2
  • Pytorch 2.3.1+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1

限制和偏见

虽然该模型在广泛的任务上表现良好,但它可能仍然会产生偏见或错误的输出。用户在使用该模型时应谨慎,并在敏感或高风险应用中保持批判性的判断。模型的输出受其训练数据的影响,可能包含固有的偏见。

道德考虑

用户应确保该模型的部署符合道德指南,并考虑所生成文本的潜在社会影响。我们强烈反对将该模型滥用于生成有害或误导性内容。

致谢

我们感谢Alibaba Cloud提供的基础模型。

联系方式

如果对此模型有任何问题或意见或建议,请联系 rubra团队

引用信息

如果您使用了这项工作,请引用如下:

@misc {rubra_ai_2024,
	author       = { Sanjay Nadhavajhala and Yingbei Tong },
	title        = { Rubra-Qwen2-7B-Instruct },
	year         = 2024,
	url          = { https://huggingface.co/rubra-ai/Qwen2-7B-Instruct },
	doi          = { 10.57967/hf/2658 },
	publisher    = { Hugging Face }
}
Description
Model synced from source: rubraAI/Qwen2-7B-Instruct
Readme 4.2 MiB