Zaddy3363/stock-ai-qwen-full
The Zaddy3363/stock-ai-qwen-full is a 7.6 billion parameter Qwen2 model, developed by Zaddy3363, and finetuned from unsloth/qwen2.5-7b-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training speeds. It is designed for applications requiring efficient and performant language understanding and generation, leveraging its 32768 token context length.
Loading preview...
Overview
The Zaddy3363/stock-ai-qwen-full is a 7.6 billion parameter Qwen2 model, developed by Zaddy3363. It was finetuned from the unsloth/qwen2.5-7b-unsloth-bnb-4bit base model, leveraging the Unsloth library and Huggingface's TRL for training. A key characteristic of this model's development is its optimized training process, which was reportedly 2x faster due to the use of Unsloth.
Key Capabilities
- Efficient Training: Benefits from Unsloth's optimizations for faster finetuning.
- Qwen2 Architecture: Based on the robust Qwen2 model family, providing strong language capabilities.
- Context Length: Supports a substantial context window of 32768 tokens, suitable for processing longer inputs.
Good For
- Applications requiring a performant 7.6B parameter model.
- Tasks that benefit from a large context window.
- Developers looking for a Qwen2-based model with an optimized training lineage.