L3.1 70 B Hanami x1

Introduction

The L3.1-70B-Hanami-X1 is a language model developed as an experimental iteration over Euryale v2.2. The model exhibits distinct improvements and preferences over previous versions, notably Euryale v2.1 and v2.2. The model is recommended for use with a minimum min_p value of 0.1 for optimal performance.

Architecture

The model is based on the Llama architecture, specifically designed to improve upon the capabilities of its predecessors. It retains compatibility with Euryale v2.1 and v2.2 settings, ensuring a seamless transition for users familiar with those models.

Training

The model has been trained to enhance language understanding and generation capabilities. The specifics of the training dataset and methodology have not been disclosed, but the model has been optimized to provide improved performance over previous versions.

Guide: Running Locally

1. Clone the Repository: Begin by cloning the model repository from Hugging Face.

   git clone https://huggingface.co/Sao10K/L3.1-70B-Hanami-x1
   

2. Install Dependencies: Ensure you have the necessary dependencies installed, including Python and the Hugging Face Transformers library.

   pip install transformers
   

3. Load the Model: Use the Transformers library to load and utilize the model.

   from transformers import AutoModel
   
   model = AutoModel.from_pretrained("Sao10K/L3.1-70B-Hanami-x1")
   

4. Cloud GPUs: For optimal performance, especially with large models like L3.1-70B-Hanami-X1, consider using cloud GPU services such as AWS, Google Cloud, or Azure.

License

The model is licensed under the CC BY-NC 4.0. This license allows for non-commercial use, sharing, and adaptation, provided appropriate credit is given and any modifications are indicated.