Edit model card

GOT THIS MODEL TO PERFORM FUNCTION CALLING HERE IS REFERENCE COLAB: https://colab.research.google.com/drive/1LL5MLMj0Sw-4redKV9C9I68g9_1IPgQN?usp=sharing

Merged with haripritam/Qwen2-fncl-adapaters-4

New prompt template inspired for NousResearch-function-calling.

<|im_start|>system
You are a helpful assistant with access to the following functions. Use them if required -
{
    "name": "generate_password",
    "description": "Generate a random password",
    "parameters": {
        "type": "object",
        "properties": {
            "length": {
                "type": "integer",
                "description": "The length of the password"
            },
            "include_symbols": {
                "type": "boolean",
                "description": "Whether to include symbols in the password"
            }
        },
        "required": [
            "length"
        ]
    }
} For each function call return a json object with function name and arguments within <toolcall></toolcall> XML tags as follows:
<toolcall>
{'name': <function-name>, 'arguments': <args-dict>}
</toolcall><|im_end|>
<|im_start|>user
I need a new password. Can you generate one for me?<|im_end|>
<|im_start|>assistant
Of course. How long would you like your password to be? And would you like it to include symbols?<|im_end|>
<|im_start|>user
I would like it to be 12 characters long and yes, please include symbols.<|im_end|>
<|im_start|>assistant
<toolcall>
{"name": "generate_password", "arguments": '{"length": 12, "include_symbols": true}'}
</toolcall><|im_end|>
<|im_start|>tool
{"password": "4&7j#9@1Q6*"}<|im_end|>
<|im_start|>assistant
Here is your new password: 4&7j#9@1Q6*. Please make sure to save it in a secure location.<|im_end|>
Downloads last month
16
Safetensors
Model size
494M params
Tensor type
FP16
·
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 haripritam/Qwen2-0.5B-fncl

Collection including haripritam/Qwen2-0.5B-fncl