shabieh2/3370_fs_260410_system_merged

Hugging Face
TEXT GENERATIONConcurrency Cost:4Model Size:70BQuant:FP8Ctx Length:8kPublished:Apr 15, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The shabieh2/3370_fs_260410_system_merged is a 70 billion parameter Llama-3.3-Instruct-based causal language model developed by shabieh2. This model was fine-tuned using Unsloth and Hugging Face's TRL library, enabling 2x faster training. With an 8192-token context length, it is optimized for instruction-following tasks.

Loading preview...

Model Overview

The shabieh2/3370_fs_260410_system_merged is a 70 billion parameter language model developed by shabieh2. It is based on the unsloth/llama-3.3-70b-instruct-unsloth-bnb-4bit architecture and features an 8192-token context length.

Key Characteristics

  • Architecture: Llama-3.3-Instruct based, with 70 billion parameters.
  • Training Efficiency: Fine-tuned using Unsloth and Hugging Face's TRL library, which facilitated 2x faster training compared to standard methods.
  • Context Length: Supports an 8192-token context window.
  • License: Distributed under the Apache-2.0 license.

Intended Use Cases

This model is suitable for applications requiring a large instruction-tuned language model, particularly where efficient fine-tuning processes are beneficial. Its Llama-3.3-Instruct base suggests strong performance in conversational AI, question answering, and general instruction-following tasks.