temp_model/README.md

BitAgent Tool-Calling Model

This model is specifically trained for tool calling tasks with special handling for distance calculations.

Model Description

This model is designed to handle tool calling tasks with specific emphasis on:

• Parameter handling for distance calculations
• Correct argument ordering for origin/destination pairs
• Function call formatting

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

# Load model and tokenizer
model = AutoModelForCausalLM.from_pretrained("Anurag02/LLM")
tokenizer = AutoTokenizer.from_pretrained("Anurag02/LLM")

# Example usage for distance calculation
prompt = """What is the distance from Los Angeles to New York? (Based on the function name, the "origin" and "destination" are flipped for the question)"""

# Generate response
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs)
response = tokenizer.decode(outputs[0])

Parameters

• Model Size: ≤ 8B parameters
• Specialized in: Tool calling tasks
• Optimized for: Distance calculations with parameter flipping

Example Outputs

For the query "What is the distance from Los Angeles to New York?":

calculate_distance(origin="New York", destination="Los Angeles")