ahmarbehroz30/roman-pashto-ai-model

TEXT GENERATIONConcurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jun 9, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The ahmarbehroz30/roman-pashto-ai-model is a 7.6 billion parameter instruction-tuned causal language model, finetuned from unsloth/qwen2.5-Coder-7B-Instruct-bnb-4bit. Developed by ahmarbehroz30, this model was trained using Unsloth and Huggingface's TRL library for accelerated finetuning. It offers a 32768 token context length and is specialized for tasks related to Roman Pashto, leveraging its efficient training methodology.

Loading preview...

Model Overview

The ahmarbehroz30/roman-pashto-ai-model is a 7.6 billion parameter instruction-tuned language model, developed by ahmarbehroz30. It is finetuned from the unsloth/qwen2.5-Coder-7B-Instruct-bnb-4bit base model, indicating a foundation in coding and instruction-following capabilities. A key aspect of its development is the use of Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.

Key Characteristics

  • Base Model: Finetuned from unsloth/qwen2.5-Coder-7B-Instruct-bnb-4bit.
  • Parameter Count: 7.6 billion parameters.
  • Context Length: Supports a substantial context window of 32768 tokens.
  • Efficient Training: Leverages Unsloth for accelerated finetuning, resulting in faster model development.

Potential Use Cases

This model is particularly suited for applications requiring a large language model with efficient training, especially within the domain of Roman Pashto, given its developer's focus. Its instruction-tuned nature and origin from a 'Coder' base suggest potential for:

  • Language Generation: Creating text in Roman Pashto.
  • Instruction Following: Responding to prompts and instructions effectively.
  • Code-related Tasks: Potentially assisting with code generation or understanding, inherited from its base model, if applied to relevant Pashto contexts.