DesiLadkaa/indian-finance-stage1-noninstruct-merged
TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 5, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The DesiLadkaa/indian-finance-stage1-noninstruct-merged model is a 1.5 billion parameter Qwen2.5-based language model, finetuned by DesiLadkaa. This model was trained using Unsloth and Huggingface's TRL library, enabling faster training. With a context length of 32768 tokens, it is designed for applications requiring processing of extensive financial text.
Loading preview...
Overview
DesiLadkaa/indian-finance-stage1-noninstruct-merged is a 1.5 billion parameter language model, finetuned by DesiLadkaa. It is based on the Qwen2.5 architecture and was developed using the Unsloth library for accelerated training and Huggingface's TRL library. This model is specifically designed for applications within the Indian finance domain.
Key Capabilities
- Efficient Training: Leverages Unsloth for 2x faster training compared to standard methods.
- Qwen2.5 Architecture: Built upon the robust Qwen2.5 foundation, providing strong language understanding capabilities.
- Domain-Specific Focus: Finetuned for the Indian finance sector, suggesting enhanced performance on related tasks.
- Extended Context: Supports a context length of 32768 tokens, suitable for processing lengthy financial documents or conversations.
Good For
- Financial Text Analysis: Ideal for tasks involving Indian financial data, reports, and documents.
- Research and Development: Provides a specialized base model for further finetuning on specific financial NLP tasks.
- Applications requiring long context: Its 32768 token context window makes it suitable for detailed analysis of financial texts.