Tail-LS/Qwen2.5-3B-dpo-finance is a 3.1 billion parameter language model based on the Qwen2.5-3B architecture. This model is fine-tuned using DPO on financial datasets, including gbharti/finance-alpaca and FinGPT/fingpt-sentiment-train. It specializes in financial domain understanding and sentiment analysis, offering a 32768 token context length. Its primary application is in financial text processing and analysis.
Loading preview...
Model Overview
Tail-LS/Qwen2.5-3B-dpo-finance is a specialized language model built upon the Qwen2.5-3B base architecture, featuring 3.1 billion parameters and a substantial 32768 token context window. This model has undergone Direct Preference Optimization (DPO) fine-tuning, specifically leveraging financial datasets such as gbharti/finance-alpaca and FinGPT/fingpt-sentiment-train.
Key Capabilities
- Financial Domain Specialization: Optimized for understanding and generating text within the financial sector.
- Sentiment Analysis: Enhanced performance on tasks related to financial sentiment, likely due to its training on relevant datasets.
- Large Context Window: Supports processing of extensive financial documents or conversations with its 32K token context length.
Good For
- Financial Text Processing: Analyzing financial reports, news articles, and market commentary.
- Financial Sentiment Analysis: Identifying and interpreting sentiment from financial data streams.
- Domain-Specific Applications: Developing applications that require deep understanding of financial terminology and concepts.