akshayballal/gemma2-2b-xlam-function-calling

Model Card for Model ID

This model is a function calling version of google/gemma-2-2b finetuned on the Salesforce/xlam-function-calling-60k dataset.

Uploaded model

• Developed by: akshayballal
• License: apache-2.0
• Finetuned from model : unsloth/gemma-2-2b-bnb-4bit

Usage

from unsloth import FastLanguageModel

max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "gemma2-2b-xlam-function-calling", # YOUR MODEL YOU USED FOR TRAINING
    max_seq_length = 1024,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
)
FastLanguageModel.for_inference(model) # Enable native 2x faster inference


alpaca_prompt = """Below are the tools that you have access to these tools. Use them if required.

### Tools:
{}

### Query:
{}

### Response:
{}"""

tools = [
    {
        "name": "upcoming",
        "description": "Fetches upcoming CS:GO matches data from the specified API endpoint.",
        "parameters": {
            "content_type": {
                "description": "The content type for the request, default is 'application/json'.",
                "type": "str",
                "default": "application/json",
            },
            "page": {
                "description": "The page number to retrieve, default is 1.",
                "type": "int",
                "default": "1",
            },
            "limit": {
                "description": "The number of matches to retrieve per page, default is 10.",
                "type": "int",
                "default": "10",
            },
        },
    }
]
query = """Can you fetch the upcoming CS:GO matches for page 1 with a 'text/xml' content type  and a limit of 20 matches? Also, can you fetch the upcoming matches for page 2 with the 'application/xml' content type and a limit of 15 matches?"""

FastLanguageModel.for_inference(model)

model_input = tokenizer(alpaca_prompt.format(tools, query, ""), return_tensors="pt")

output = model.generate(**input, max_new_tokens=1024, temperature = 0.0)

decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)