shareit/chabot-supervisor-phi4KLv2

TEXT GENERATIONConcurrency Cost:1Model Size:14.7BQuant:FP8Ctx Length:32kPublished:Apr 13, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The shareit/chabot-supervisor-phi4KLv2 is a 14.7 billion parameter Phi-3 model developed by shareit, fine-tuned from unsloth/phi-4-reasoning-plus-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. It features a 32768 token context length, making it suitable for applications requiring extensive contextual understanding.

Loading preview...

Model Overview

The shareit/chabot-supervisor-phi4KLv2 is a 14.7 billion parameter Phi-3 model developed by shareit. It was fine-tuned from the unsloth/phi-4-reasoning-plus-unsloth-bnb-4bit base model, leveraging the Unsloth library and Huggingface's TRL for efficient training.

Key Characteristics

  • Architecture: Phi-3 based, fine-tuned for specific applications.
  • Parameter Count: 14.7 billion parameters.
  • Context Length: Supports a substantial 32768 token context window.
  • Training Efficiency: Achieved 2x faster training due to the integration of Unsloth and Huggingface's TRL library.

Potential Use Cases

This model is well-suited for tasks that benefit from a large context window and the reasoning capabilities inherent in the Phi-3 architecture. Its efficient training process suggests it could be a strong candidate for applications requiring specialized fine-tuning without extensive computational overhead.