Weyaxi/OpenHermes-2.5-neural-chat-v3-3-openchat-3.5-1210-Slerp

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Dec 24, 2023License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Weyaxi/OpenHermes-2.5-neural-chat-v3-3-openchat-3.5-1210-Slerp is a 7 billion parameter language model created by Weyaxi, built upon the Mistral-7B-v0.1 base architecture. This model is a Slerp merge of OpenHermes-2.5-neural-chat-v3-3-Slerp and openchat-3.5-1210, designed to combine their respective strengths. It is suitable for general conversational AI tasks, leveraging the combined capabilities of its merged components.

Loading preview...

Model Overview

Weyaxi/OpenHermes-2.5-neural-chat-v3-3-openchat-3.5-1210-Slerp is a 7 billion parameter language model developed by Weyaxi. It is constructed using a Slerp merge method via mergekit, combining two distinct models: Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp and openchat/openchat-3.5-1210. The base model for this merge is mistralai/Mistral-7B-v0.1.

Key Characteristics

  • Architecture: Based on the Mistral-7B-v0.1 foundation.
  • Merging Technique: Utilizes the Slerp (Spherical Linear Interpolation) merge method, which blends the weights of the source models.
  • Source Models: Integrates features from OpenHermes-2.5-neural-chat-v3-3-Slerp and openchat-3.5-1210 to potentially enhance performance across various tasks.
  • Parameter Configuration: Specific t values were applied during the merge for self-attention and MLP layers, indicating a fine-tuned blending strategy for different parts of the neural network.
  • Tokenizer: Employs a union tokenizer source, aiming for comprehensive vocabulary coverage from the merged models.

Potential Use Cases

This model is designed for general-purpose conversational AI and text generation, benefiting from the combined strengths of its constituent models. It can be considered for applications requiring a balanced performance profile derived from multiple specialized models.