Gangesh-Chaudhary-241562452/sanatan-gita-guru-full

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Apr 4, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The Gangesh-Chaudhary-241562452/sanatan-gita-guru-full is a 7 billion parameter Mistral-based causal language model, finetuned by Gangesh-Chaudhary-241562452. It was developed using Unsloth and Huggingface's TRL library, enabling 2x faster training. This model is derived from MaziyarPanahi/airoboros-m-7b-3.1.2-dare-0.85-Mistral-7B-Instruct-v0.2-slerp, focusing on specialized applications through its finetuning process.

Loading preview...

Model Overview

The Gangesh-Chaudhary-241562452/sanatan-gita-guru-full is a 7 billion parameter language model developed by Gangesh-Chaudhary-241562452. It is a finetuned variant of the MaziyarPanahi/airoboros-m-7b-3.1.2-dare-0.85-Mistral-7B-Instruct-v0.2-slerp model, built upon the Mistral architecture.

Key Characteristics

  • Base Model: Mistral-7B-Instruct-v0.2 architecture.
  • Training Efficiency: Finetuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • Parameter Count: 7 billion parameters, offering a balance between performance and computational requirements.
  • License: Released under the Apache-2.0 license.

Potential Use Cases

This model is suitable for applications requiring a specialized instruction-tuned Mistral-based LLM, particularly where the specific finetuning objectives of the original airoboros-m-7b model are beneficial. Its efficient training methodology suggests it could be a good candidate for further domain-specific adaptations or for deployment in environments where optimized performance is crucial.