kairawal/Llama-3.2-3B-Instruct-DA-SynthDolly-r16alpha32-E3-S73

TEXT GENERATIONConcurrency Cost:1Model Size:3.2BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:May 14, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

kairawal/Llama-3.2-3B-Instruct-DA-SynthDolly-r16alpha32-E3-S73 is a 3.2 billion parameter instruction-tuned Llama model developed by kairawal, fine-tuned from unsloth/llama-3.2-3b-Instruct. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for general instruction-following tasks, leveraging its efficient training methodology.

Loading preview...

Overview

kairawal/Llama-3.2-3B-Instruct-DA-SynthDolly-r16alpha32-E3-S73 is a 3.2 billion parameter instruction-tuned language model developed by kairawal. It is based on the Llama architecture, specifically fine-tuned from the unsloth/llama-3.2-3b-Instruct model. A key characteristic of this model is its efficient training process, which was accelerated by 2x using the Unsloth library in conjunction with Huggingface's TRL library.

Key Capabilities

  • Instruction Following: Designed to understand and execute instructions effectively.
  • Efficient Training: Benefits from optimized training techniques, making it a potentially resource-friendly option for various applications.

Good For

  • Developers seeking a compact yet capable instruction-tuned Llama model.
  • Applications requiring efficient inference due to its smaller parameter count.
  • Experimentation with models trained using Unsloth's acceleration methods.