Edit model card

Qwen2-7B-Instruct-glaive-function-calling

Introduction

基于数据集 glaive-function-calling-v2 在 Qwen2-7B-Instruct 上进行微调而来

Training details

使用 lora 进行训练 训练样本如下:

<|im_start|>system
You are a helpful assistant with access to the following functions. Use them if required -
{
    "name": "generate_invoice",
    "description": "Generate an invoice with specified details",
    "parameters": {
        "type": "object",
        "properties": {
            "customer_name": {
                "type": "string",
                "description": "The name of the customer"
            },
            "items": {
                "type": "array",
                "items": {
                    "type": "object",
                    "properties": {
                        "name": {
                            "type": "string",
                            "description": "The name of the item"
                        },
                        "quantity": {
                            "type": "integer",
                            "description": "The quantity of the item"
                        },
                        "price": {
                            "type": "number",
                            "description": "The price of the item"
                        }
                    },
                    "required": [
                        "name",
                        "quantity",
                        "price"
                    ]
                }
            }
        },
        "required": [
            "customer_name",
            "items"
        ]
    }
}
<|im_end|>
<|im_start|>user
I need to generate an invoice for a customer named John Doe. He bought 2 apples for $1 each and 3 oranges for $2 each.<|im_end|>
<|im_start|>assistant
<functioncall> {"name": "generate_invoice", "arguments": '{"customer_name": "John Doe", "items": [{"name": "apple", "quantity": 2, "price": 1}, {"name": "orange", "quantity": 3, "price": 2}]}'} <|endoftext|><|im_end|>
<|im_start|>function
{"invoice_id": "INV12345", "customer_name": "John Doe", "items": [{"name": "apple", "quantity": 2, "price": 1, "total": 2}, {"name": "orange", "quantity": 3, "price": 2, "total": 6}], "total": 8, "status": "Generated"}<|im_end|>
<|im_start|>assistant
The invoice has been successfully generated. The invoice ID is INV12345. The total amount for 2 apples and 3 oranges is $8. <|endoftext|><|im_end|>

Quickstart

参考 Qwen2-7B-Instruct

Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2-7B-Instruct",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-7B-Instruct")

prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(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]
Downloads last month
10
Safetensors
Model size
7.62B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train xalss/Qwen2-7B-Instruct-glaive-function-calling

Space using xalss/Qwen2-7B-Instruct-glaive-function-calling 1