hafidhsoekma/gasing-edu-16bit

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kLicense:apache-2.0Architecture:Transformer Open Weights Cold

The hafidhsoekma/gasing-edu-16bit is a 7.6 billion parameter Qwen2.5-based instruction-tuned causal language model developed by hafidhsoekma. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. This model is optimized for general instruction-following tasks, leveraging its Qwen2.5 architecture for robust performance.

Loading preview...

Model Overview

The hafidhsoekma/gasing-edu-16bit is a 7.6 billion parameter instruction-tuned language model based on the Qwen2.5 architecture. Developed by hafidhsoekma, this model was fine-tuned from unsloth/Qwen2.5-7B-Instruct-unsloth-bnb-4bit.

Key Characteristics

  • Architecture: Qwen2.5-based, a powerful causal language model family.
  • Training Efficiency: Fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • Parameter Count: Features 7.6 billion parameters, offering a balance between performance and computational requirements.
  • Context Length: Supports a substantial context window of 131,072 tokens, allowing for processing and generating longer sequences of text.

Use Cases

This model is suitable for a variety of general-purpose instruction-following tasks, benefiting from its efficient training and robust base architecture. Its large context window makes it particularly effective for applications requiring extensive input or generating detailed, lengthy responses.