eachadea/legacy-vicuna-13b

TEXT GENERATIONConcurrency Cost:1Model Size:13BQuant:FP8Ctx Length:4kPublished:Apr 3, 2023Architecture:Transformer0.1K Cold

The eachadea/legacy-vicuna-13b is a 13 billion parameter language model based on the Vicuna architecture, developed by eachadea. This model is an older version of the Vicuna-13B series, offering general-purpose conversational capabilities. It is primarily suited for tasks requiring a foundational understanding of language and dialogue generation, with a context length of 4096 tokens.

Loading preview...

Overview

The eachadea/legacy-vicuna-13b is a 13 billion parameter language model, representing an earlier iteration of the Vicuna-13B series. Developed by eachadea, this model provides foundational capabilities for various natural language processing tasks. It operates with a context length of 4096 tokens, making it suitable for processing moderately sized inputs and generating coherent responses.

Key Characteristics

  • Model Size: 13 billion parameters, offering a balance between performance and computational requirements.
  • Architecture: Based on the Vicuna architecture, known for its conversational abilities.
  • Context Window: Supports a 4096-token context length, allowing for reasonable input and output sequences.

Important Note

This model is explicitly marked as a legacy version. Users are strongly advised to migrate to the newer and improved version available at https://huggingface.co/eachadea/vicuna-13b-1.1 for enhanced performance, stability, and updated features. The legacy model may not receive further updates or support.