Phuc-HugigFace/Qwen3.5-2B-Vi-SFT

VISIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2.3BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 10, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

Phuc-HugigFace/Qwen3.5-2B-Vi-SFT is a 2.3 billion parameter language model developed by Phuc-HugigFace, fine-tuned from Qwen/Qwen3.5-2B-Base. This model was trained using Unsloth and Huggingface's TRL library, enabling faster training times. It is designed for general language understanding and generation tasks, leveraging its Qwen3.5 base architecture.

Loading preview...

Model Overview

Phuc-HugigFace/Qwen3.5-2B-Vi-SFT is a 2.3 billion parameter language model developed by Phuc-HugigFace. It is a fine-tuned version of the Qwen/Qwen3.5-2B-Base model, indicating its foundation in the Qwen3.5 architecture.

Training Methodology

A key differentiator for this model is its training process. It was fine-tuned using Unsloth in conjunction with Huggingface's TRL library. This combination allowed for a 2x faster training speed compared to standard methods, making it an efficient iteration on the base model.

Licensing

The model is released under the Apache-2.0 license, which permits broad use, modification, and distribution.

Potential Use Cases

Given its base in the Qwen3.5 series and efficient fine-tuning, this model is suitable for various natural language processing tasks where a compact yet capable model is desired, especially in scenarios benefiting from faster development cycles due to its optimized training.