AiHub4MSRH-Hash/sunflower-14b-sft-hash-english-16bit-v2

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:14BQuant:FP8Ctx Length:32kPublished:Mar 2, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

AiHub4MSRH-Hash/sunflower-14b-sft-hash-english-16bit-v2 is a 14 billion parameter Qwen3-based causal language model developed by AiHub4MSRH-Hash, fine-tuned from Sunbird/Sunflower-14B. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training speeds. It is designed for general language tasks, leveraging its efficient fine-tuning process to provide a capable English language model.

Loading preview...

Model Overview

AiHub4MSRH-Hash/sunflower-14b-sft-hash-english-16bit-v2 is a 14 billion parameter language model based on the Qwen3 architecture. Developed by AiHub4MSRH-Hash, this model is a fine-tuned version of the Sunbird/Sunflower-14B base model, licensed under Apache-2.0.

Key Characteristics

  • Architecture: Qwen3-based causal language model.
  • Parameter Count: 14 billion parameters, offering a balance between performance and computational requirements.
  • Training Efficiency: Notably, the model was fine-tuned using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process compared to standard methods.
  • Context Length: Supports a context length of 32768 tokens, allowing for processing longer inputs and generating more coherent and extended outputs.

Intended Use Cases

This model is suitable for a variety of English language processing tasks, benefiting from its efficient fine-tuning and substantial parameter count. Its optimized training process suggests a focus on delivering strong performance for general-purpose applications.