Nera_ Noctis 12 B

Nitral-AI

Nera_Noctis-12B

Introduction

Nera_Noctis-12B is a language model developed by Nitral-AI and available on Hugging Face. It utilizes the Safetensors library and is designed for use with English language tasks. The model is associated with the "mistral" category and is distributed under a custom license specified as "other."

Architecture

The Nera_Noctis-12B model architecture is optimized to handle complex language processing tasks. It supports a prompt format compatible with CHATML, which allows for structured interaction between users and the system.

Training

While specific training details are not provided, the model supports importing instructions and context to enhance text generation capabilities. Users can access pre-defined presets that combine instruction/context import and text generation settings for improved performance.

Guide: Running Locally

To run Nera_Noctis-12B locally, follow these general steps:

  1. Install Required Libraries: Ensure you have Python and the necessary libraries installed, such as Hugging Face's transformers library.
  2. Download the Model: Access the model files from the Nera_Noctis-12B repository on Hugging Face.
  3. Load the Model: Use the transformers library to load the model and tokenizer.
  4. Run Inference: Provide input prompts in the specified CHATML format and generate responses using the model.

For optimal performance, consider using cloud-based GPUs from providers such as AWS, Google Cloud, or Azure.

License

The Nera_Noctis-12B model is distributed under a custom license type referred to as "other." Users should refer to the specific license details on the model's Hugging Face page for more information.

More Related APIs