MadeAgents/Hammer-7b

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 2, 2024License:cc-by-4.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

MadeAgents/Hammer-7b is a 7.6 billion parameter large language model, fine-tuned from the Qwen 2.0 series, specifically designed for robust function calling. It optimizes performance through advanced training techniques, including function masking, and is trained on the APIGen Function Calling Datasets. This model excels at enabling AI agents to accurately select and execute functions, making it ideal for on-device agentic applications.

Loading preview...

Overview

MadeAgents/Hammer-7b is a 7.6 billion parameter model from the Hammer series, developed by MadeAgents. It is specifically engineered to enhance the function calling capabilities of AI agents, distinguishing itself by optimizing performance through advanced training techniques rather than solely data refinement. The model is fine-tuned based on the Qwen 2.0 series and utilizes a function masking technique.

Key Capabilities

  • Robust Function Calling: Hammer-7b demonstrates strong and stable performance across various function calling benchmarks, including the Berkeley Function-Calling Leaderboard (BFCL-v2), where it achieves state-of-the-art results at its scale.
  • Optimized Training: The model's performance is driven by advanced training techniques, including function masking, and it was trained using the APIGen Function Calling Datasets (60,000 samples) supplemented by the xlam-irrelevance-7.5k dataset.
  • On-Device Application Focus: Designed with a focus on on-device applications, making it suitable for building personalized and agentic applications that require efficient function execution.

Use Cases

  • AI Agent Development: Ideal for developers building AI agents that need to reliably call external functions or tools based on user queries.
  • On-Device Applications: Suitable for integrating advanced function-calling capabilities into applications running on edge devices.
  • Tool-Use Scenarios: Excels in scenarios where an LLM needs to select and execute specific tools or APIs to fulfill complex requests, as demonstrated by its strong benchmark performance.

Finetunes
1 models