sanaeai/Qwen2.5-14B-FinCausal-Rep

TEXT GENERATIONConcurrency Cost:1Model Size:14.8BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Feb 19, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The sanaeai/Qwen2.5-14B-FinCausal-Rep is a 14.8 billion parameter Qwen2.5-based causal language model, fine-tuned from Qwen/Qwen2.5-14B-Instruct-1M. This model was developed by sanaeai and optimized for faster training using Unsloth and Huggingface's TRL library. It is designed for financial causal reasoning tasks, leveraging its instruction-tuned base for specialized applications. The model's efficient training process allows for rapid deployment in financial analysis and related domains.

Loading preview...

Model Overview

The sanaeai/Qwen2.5-14B-FinCausal-Rep is a 14.8 billion parameter language model, fine-tuned by sanaeai from the Qwen/Qwen2.5-14B-Instruct-1M base model. This model leverages the robust architecture of Qwen2.5 and its instruction-following capabilities, specifically adapting it for financial causal reasoning tasks.

Key Differentiators

  • Efficient Fine-tuning: This model was fine-tuned significantly faster using Unsloth and Huggingface's TRL library, indicating an optimized training process.
  • Specialized Domain: While the exact dataset is not specified, the 'FinCausal' in its name suggests a specialization in financial causal analysis, making it distinct from general-purpose LLMs.
  • Qwen2.5 Base: Built upon the Qwen2.5-14B-Instruct-1M, it inherits strong instruction-following and general language understanding capabilities, which are then applied to a specific domain.

Use Cases

This model is particularly suited for applications requiring:

  • Financial Causal Analysis: Identifying cause-and-effect relationships within financial texts and data.
  • Specialized Instruction Following: Executing instructions tailored to financial contexts.
  • Efficient Deployment: Its optimized training suggests potential for faster iteration and deployment in financial AI projects.