Entropicengine/Trifecta-L3-8b

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kArchitecture:Transformer0.0K Cold

Entropicengine/Trifecta-L3-8b is an 8 billion parameter language model created by Entropicengine through a DARE TIES merge of NousResearch/Hermes-3-Llama-3.1-8B, Sao10K/L3-8B-Lunaris-v1, and Sao10K/L3-8B-Stheno-v3.2. This merged model leverages the strengths of its constituent models, with Sao10K/L3-8B-Stheno-v3.2 serving as the base. It is designed for general language generation tasks, combining diverse capabilities from its merged components.

Loading preview...

Entropicengine/Trifecta-L3-8b Overview

Trifecta-L3-8b is an 8 billion parameter language model developed by Entropicengine. It was created using the DARE TIES merge method, which combines multiple pre-trained models to enhance overall performance and capabilities.

Merge Details

This model is a composite of three distinct language models, with Sao10K/L3-8B-Stheno-v3.2 serving as the foundational base model. The other merged components include:

  • NousResearch/Hermes-3-Llama-3.1-8B
  • Sao10K/L3-8B-Lunaris-v1
  • Sao10K/L3-8B-Stheno-v3.2 (base model)

The merge configuration utilized specific weighting and density parameters for each component, aiming to integrate their respective strengths. The model uses the llama3 chat template and processes outputs in bfloat16 precision.

Intended Use Cases

As a merged model, Trifecta-L3-8b is suitable for a variety of general-purpose language generation tasks, benefiting from the combined knowledge and reasoning abilities of its constituent models. Its 8192-token context length supports processing moderately long inputs.