gjyotin305/Llama-3.2-3B-Instruct_old_sft_alpaca_009

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:3.2BQuant:BF16Ctx Length:32kPublished:Jan 8, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

gjyotin305/Llama-3.2-3B-Instruct_old_sft_alpaca_009 is a 3.2 billion parameter instruction-tuned causal language model developed by gjyotin305. This model is a fine-tuned variant of the Llama-3.2-3B-Instruct architecture, optimized for performance and efficiency. It was trained using Unsloth and Huggingface's TRL library, making it suitable for general instruction-following tasks.

Loading preview...

Model Overview

gjyotin305/Llama-3.2-3B-Instruct_old_sft_alpaca_009 is a 3.2 billion parameter instruction-tuned language model developed by gjyotin305. It is based on the Llama-3.2-3B-Instruct architecture and has been fine-tuned for enhanced performance.

Key Characteristics

  • Architecture: Llama-3.2-3B-Instruct base model.
  • Parameter Count: 3.2 billion parameters, offering a balance between capability and computational efficiency.
  • Training Efficiency: Fine-tuned using Unsloth and Huggingface's TRL library, which enabled 2x faster training.
  • Context Length: Supports a context window of 32768 tokens.

Use Cases

This model is designed for general instruction-following tasks, making it suitable for applications requiring a compact yet capable language model. Its efficient training process suggests it could be a good candidate for scenarios where rapid iteration or deployment on resource-constrained environments is important.