tobil/qmd-query-expansion-qwen3.5-2B
VISIONConcurrent Unit Cost:1Model Size:2.3BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Mar 5, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold
The tobil/qmd-query-expansion-qwen3.5-2B is a 2.3 billion parameter causal language model, finetuned from unsloth/Qwen3.5-2B. Developed by tobil, this model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for query expansion tasks, leveraging its Qwen3.5 architecture and a 32768 token context length.
Loading preview...
Model Overview
The tobil/qmd-query-expansion-qwen3.5-2B is a 2.3 billion parameter language model developed by tobil. It is finetuned from the unsloth/Qwen3.5-2B base model, utilizing the Qwen3.5 architecture. A key characteristic of this model is its optimized training process, which was achieved 2x faster using the Unsloth library in conjunction with Huggingface's TRL library.
Key Capabilities
- Query Expansion: Specifically designed and finetuned for tasks related to expanding search queries.
- Efficient Training: Benefits from Unsloth's optimizations, enabling faster model development and iteration.
- Qwen3.5 Architecture: Leverages the robust capabilities of the Qwen3.5 model family.
- Extended Context: Supports a context length of 32768 tokens, allowing for processing longer inputs relevant to query expansion.
Good For
- Developers and researchers focused on improving search relevance through query expansion.
- Applications requiring a compact yet capable model for text generation and understanding in the context of search.
- Projects that prioritize efficient model training and deployment.