DesiLadkaa/indian-finance-stage3-dpo-final

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 6, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

DesiLadkaa/indian-finance-stage3-dpo-final is a 1.5 billion parameter Qwen2-based model developed by DesiLadkaa, fine-tuned for Indian finance applications. This model was trained using Unsloth and Huggingface's TRL library, offering a 32768 token context length. It is specifically optimized for tasks within the Indian financial domain, building upon its stage2 supervised fine-tuning.

Loading preview...

Model Overview

DesiLadkaa/indian-finance-stage3-dpo-final is a 1.5 billion parameter language model developed by DesiLadkaa, building on the Qwen2 architecture. This model has been fine-tuned specifically for applications within the Indian financial sector, leveraging its predecessor, DesiLadkaa/indian-finance-stage2-sft-merged.

Key Characteristics

  • Architecture: Based on the Qwen2 model family.
  • Parameter Count: 1.5 billion parameters.
  • Context Length: Supports a substantial context window of 32768 tokens.
  • Training Efficiency: The model was trained with enhanced speed using Unsloth and Huggingface's TRL library, indicating an optimized training process.
  • License: Distributed under the Apache-2.0 license.

Primary Use Case

This model is specifically designed and optimized for tasks related to Indian finance. Its fine-tuning process suggests a strong capability in understanding and generating content relevant to financial contexts within India, making it suitable for specialized applications in this domain.