HarithSami/qwen2.5-14b-instruct-arabic-yt-merged

TEXT GENERATIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:14.8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 6, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The HarithSami/qwen2.5-14b-instruct-arabic-yt-merged model is a 14.8 billion parameter instruction-tuned Qwen2.5 model developed by HarithSami. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. This model is designed for instruction-following tasks, leveraging its Qwen2.5 architecture for general language understanding and generation.

Loading preview...

Model Overview

The HarithSami/qwen2.5-14b-instruct-arabic-yt-merged is a 14.8 billion parameter instruction-tuned language model, developed by HarithSami. It is based on the Qwen2.5 architecture and was fine-tuned from the unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit model.

Key Characteristics

  • Architecture: Qwen2.5, a powerful transformer-based model known for its capabilities in various language tasks.
  • Parameter Count: 14.8 billion parameters, offering a balance between performance and computational efficiency.
  • Training Efficiency: The model was fine-tuned using Unsloth and Huggingface's TRL library, which significantly accelerated the training process.
  • Instruction-Tuned: Optimized for understanding and following human instructions, making it suitable for conversational AI, question answering, and other prompt-based applications.

Potential Use Cases

  • Instruction Following: Excels at responding to diverse prompts and carrying out specific instructions.
  • Text Generation: Capable of generating coherent and contextually relevant text based on given inputs.
  • Conversational AI: Can be integrated into chatbots and virtual assistants for engaging dialogues.

This model is released under the Apache-2.0 license, providing flexibility for various applications.

Finetunes
2 models