taylanirak/sempas-scribe-14b

TEXT GENERATIONConcurrent Unit Cost:1Model Size:14.8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 15, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

taylanirak/sempas-scribe-14b is a 14.8 billion parameter Qwen2.5-based causal language model developed by taylanirak, fine-tuned from unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It features a 32768 token context length, making it suitable for tasks requiring extensive contextual understanding.

Loading preview...

Model Overview

taylanirak/sempas-scribe-14b is a 14.8 billion parameter language model developed by taylanirak. It is fine-tuned from the unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit base model, leveraging the Qwen2.5 architecture. This model was specifically trained using the Unsloth library in conjunction with Huggingface's TRL library, which enabled a 2x acceleration in the training process.

Key Characteristics

  • Architecture: Qwen2.5-based, fine-tuned from an instruction-tuned variant.
  • Parameter Count: 14.8 billion parameters.
  • Context Length: Supports a substantial context window of 32768 tokens.
  • Training Efficiency: Utilizes Unsloth for optimized and faster training.

Potential Use Cases

Given its foundation in an instruction-tuned Qwen2.5 model and its significant context length, taylanirak/sempas-scribe-14b is well-suited for applications requiring:

  • Complex Instruction Following: Handling detailed and multi-step instructions.
  • Long-form Content Generation: Generating or summarizing extensive texts due to its large context window.
  • Conversational AI: Maintaining coherent and contextually relevant dialogues over extended interactions.

This model is licensed under Apache-2.0.