mosama/LFM2.5-350M-Tool-Calling-Merged-v3
TEXT GENERATIONConcurrency Cost:1Model Size:0.35BQuant:BF16Ctx Length:32kPublished:May 14, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold
The mosama/LFM2.5-350M-Tool-Calling-Merged-v3 is a 0.35 billion parameter language model developed by mosama, fine-tuned for tool-calling capabilities. This model was trained using Unsloth and Huggingface's TRL library, enabling faster training. It is designed for applications requiring efficient function calling and integration with external tools.
Loading preview...
Overview
The mosama/LFM2.5-350M-Tool-Calling-Merged-v3 is a compact 0.35 billion parameter language model developed by mosama. It is a fine-tuned iteration of the mosama/LFM2.5-350M-Tool-Calling-Merged-v2 model, specifically optimized for tool-calling functionalities.
Key Capabilities
- Tool Calling: This model is specialized in understanding and generating responses that involve calling external tools or functions, making it suitable for agentic workflows.
- Efficient Training: The model was trained with Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
Good For
- Function Calling: Ideal for applications where the LLM needs to interact with APIs, databases, or other software tools by generating structured function calls.
- Resource-Constrained Environments: Its relatively small size (0.35B parameters) makes it suitable for deployment in environments with limited computational resources.
- Rapid Prototyping: The efficient training methodology suggests it can be quickly adapted or fine-tuned for specific tool-calling scenarios.