DesiLadkaa/indian-finance-stage3-final-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-stage3-final-v2 is a 1.5 billion parameter Qwen2 model, finetuned by DesiLadkaa from DesiLadkaa/indian-finance-stage2-merged-v2. Optimized for financial applications, this model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It features a 32768 token context length, making it suitable for processing extensive financial documents and data.

Loading preview...

Model Overview

DesiLadkaa/indian-finance-stage3-final-v2 is a 1.5 billion parameter Qwen2 model developed by DesiLadkaa. It is a finetuned version of the DesiLadkaa/indian-finance-stage2-merged-v2 model, specifically designed for applications within the Indian finance domain. The model was trained efficiently using Unsloth and Huggingface's TRL library, which enabled a 2x speedup in the training process.

Key Characteristics

  • Architecture: Qwen2
  • Parameters: 1.5 billion
  • Context Length: 32768 tokens, allowing for comprehensive analysis of long financial texts.
  • Training Efficiency: Utilizes Unsloth for accelerated finetuning.
  • License: Apache-2.0, providing flexibility for commercial and research use.

Use Cases

This model is particularly well-suited for tasks requiring an understanding of Indian financial contexts, leveraging its specialized finetuning. Its large context window makes it ideal for:

  • Analyzing financial reports and documents.
  • Processing and summarizing financial news.
  • Assisting with financial data interpretation specific to the Indian market.

Finetunes
1 models