Hugging Face Overview
WiroAI-Finance-Qwen-7B: Specialized Financial Language Model
WiroAI-Finance-Qwen-7B is a 7.6 billion parameter language model developed by WiroAI, specifically adapted for the finance domain. Built upon the Qwen architecture, this model has undergone Supervised Fine-Tuning (SFT) using the LoRA method, without quantization, to enhance its financial knowledge and reasoning capabilities.
Key Capabilities
- Finance Expertise: Fine-tuned with over 500,000 high-quality finance instructions from datasets like Josephgflowers/Finance-Instruct-500k, enabling deep understanding and generation of finance-specific content.
- Qwen Architecture: Leverages the robust foundation of the Qwen model family, providing a strong base for its specialized performance.
- High Context Length: Supports a context length of 131,072 tokens, allowing for processing and understanding of extensive financial documents and complex scenarios.
Usage and Licensing
This model is intended for applications requiring in-depth financial analysis, question answering, and content generation. It is provided under the Apache 2.0 license, allowing for flexible use. Developers can integrate the model using the Hugging Face Transformers pipeline, with examples provided for quick setup and inference.