mosama/LFM2.5-350M-Tool-Calling-Merged-v3-chat-template-updated
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.35BQuant:BF16Context Size:32kPublished:May 22, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The mosama/LFM2.5-350M-Tool-Calling-Merged-v3-chat-template-updated is a 0.35 billion parameter language model developed by mosama, fine-tuned from mosama/LFM2.5-350M-Tool-Calling-Merged-v3. This model was trained using Unsloth, enabling 2x faster training. It is designed for tool-calling applications, leveraging its compact size and efficient training for specialized tasks.
Loading preview...
Model Overview
The mosama/LFM2.5-350M-Tool-Calling-Merged-v3-chat-template-updated is a compact 0.35 billion parameter language model developed by mosama. It is a fine-tuned version of the mosama/LFM2.5-350M-Tool-Calling-Merged-v3 model, specifically updated with a chat template.
Key Characteristics
- Efficient Training: This model was trained with Unsloth, which facilitated a 2x faster training process compared to conventional methods.
- Tool-Calling Focus: The model's lineage and naming suggest an optimization for tool-calling functionalities, making it suitable for applications requiring interaction with external tools or APIs.
- Compact Size: With 0.35 billion parameters, it offers a balance between performance and computational efficiency, ideal for deployment in resource-constrained environments or for specific, targeted tasks.
Good For
- Applications requiring efficient tool-calling capabilities.
- Scenarios where a smaller, faster-trained model is advantageous.
- Integration into systems that benefit from a chat-templated language model for structured interactions.