RinKana/finance-gemma4-e2b

VISIONConcurrency Cost:1Model Size:5.1BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 26, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

RinKana/finance-gemma4-e2b is a 5.1 billion parameter Gemma-4-e2b-it causal language model developed by RinKana. This model is specifically fine-tuned for financial applications, leveraging the Gemma architecture for efficient processing. It was trained using Unsloth and Huggingface's TRL library, enabling 2x faster fine-tuning. With a 32768 token context length, it is optimized for handling extensive financial texts and data.

Loading preview...

Model Overview

RinKana/finance-gemma4-e2b is a 5.1 billion parameter language model, fine-tuned by RinKana from the unsloth/gemma-4-e2b-it-unsloth-bnb-4bit base model. This model is designed with a substantial context length of 32768 tokens, making it suitable for processing lengthy documents and complex data structures.

Key Characteristics

  • Architecture: Based on the Gemma-4-e2b-it family, known for its efficiency and performance.
  • Parameter Count: Features 5.1 billion parameters, offering a balance between capability and computational requirements.
  • Training Efficiency: Fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • Context Length: Supports a 32768 token context window, ideal for tasks requiring extensive contextual understanding.

Intended Use Cases

This model is specifically developed for applications within the finance domain. Its fine-tuning and large context window suggest suitability for tasks such as:

  • Analyzing financial reports and documents.
  • Processing market data and news.
  • Assisting with financial research and information extraction.
  • Developing applications that require deep understanding of financial texts.

Finetunes
2 models