DesiLadkaa/indian-finance-stage2-merged-v2

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 9, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

DesiLadkaa/indian-finance-stage2-merged-v2 is a 1.5 billion parameter Qwen2 model developed by DesiLadkaa, fine-tuned from DesiLadkaa/indian-finance-stage1-merged-v2. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. With a 32768 token context length, it is optimized for financial applications within the Indian context.

Loading preview...

Model Overview

DesiLadkaa/indian-finance-stage2-merged-v2 is a 1.5 billion parameter Qwen2 model, developed by DesiLadkaa. It represents the second stage of fine-tuning, building upon the previously released DesiLadkaa/indian-finance-stage1-merged-v2 model.

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 fine-tuned with a focus on efficiency, utilizing Unsloth and Huggingface's TRL library, which enabled 2x faster training compared to standard methods.
  • License: Distributed under the Apache-2.0 license.

Intended Use

This model is specifically designed for applications requiring language understanding and generation within the Indian financial domain. Its fine-tuned nature suggests enhanced performance for tasks related to Indian finance, making it suitable for:

  • Financial text analysis.
  • Information extraction from financial documents.
  • Question answering on financial topics relevant to India.
  • Generating financial summaries or reports.

Finetunes
1 models