HarithSami/qwen2.5-7b-instruct-arabic-yt-merged

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 6, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

HarithSami/qwen2.5-7b-instruct-arabic-yt-merged is a 7.6 billion parameter instruction-tuned causal language model developed by HarithSami. This model is finetuned from unsloth/qwen2.5-7b-instruct and was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general instruction-following tasks, likely with a focus on Arabic language processing given the model name's indication.

Loading preview...

Model Overview

HarithSami/qwen2.5-7b-instruct-arabic-yt-merged is a 7.6 billion parameter instruction-tuned language model, developed by HarithSami. It is built upon the unsloth/qwen2.5-7b-instruct base model and utilizes the Unsloth library in conjunction with Huggingface's TRL for efficient finetuning, achieving 2x faster training speeds.

Key Characteristics

  • Base Model: Finetuned from unsloth/qwen2.5-7b-instruct.
  • Parameter Count: 7.6 billion parameters, offering a balance between performance and computational efficiency.
  • Training Efficiency: Leverages Unsloth and Huggingface's TRL library for optimized and accelerated training.
  • License: Released under the Apache-2.0 license, allowing for broad usage and distribution.

Potential Use Cases

This model is suitable for a variety of instruction-following tasks, particularly where efficient deployment and inference are desired. Given the 'arabic-yt-merged' in its name, it likely has enhanced capabilities for:

  • Arabic Language Processing: Generating and understanding text in Arabic.
  • Instruction Following: Responding to prompts and instructions effectively.
  • General NLP Tasks: Text summarization, question answering, and content generation.

Finetunes
3 models