KobeBeef67/llama32-3b-finetuned

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:3.2BQuant:BF16Ctx Length:32kPublished:Feb 22, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

KobeBeef67/llama32-3b-finetuned is a 3.2 billion parameter Llama-based causal language model developed by KobeBeef67. Finetuned from unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit, this model was trained 2x faster using Unsloth and Huggingface's TRL library. It features a 32768 token context length, making it suitable for tasks requiring extensive context processing.

Loading preview...

Model Overview

KobeBeef67/llama32-3b-finetuned is a 3.2 billion parameter Llama-based language model developed by KobeBeef67. This model is a finetuned version of unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit and was specifically optimized for training speed.

Key Characteristics

  • Architecture: Llama-based, 3.2 billion parameters.
  • Context Length: Supports a substantial context window of 32768 tokens.
  • Training Efficiency: Achieved 2x faster training by leveraging the Unsloth library in conjunction with Huggingface's TRL library.
  • License: Distributed under the Apache-2.0 license.

Intended Use Cases

This model is suitable for applications where a compact yet capable Llama-based model with a large context window is beneficial. Its optimized training process suggests potential for efficient deployment and further fine-tuning for specific tasks.