arcee-ai/Biomistral-Clown-Slerp

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:4kTool Calling:SupportedPublished:Mar 11, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

Biomistral-Clown-Slerp is a 7 billion parameter language model created by arcee-ai, formed by merging BioMistral/BioMistral-7B and CorticalStack/pastiche-crown-clown-7b-dare-dpo using a slerp merge method. This model combines the characteristics of its base models, offering a unique blend for diverse natural language processing tasks. It is designed for general-purpose applications where a merged model's distinct properties are beneficial.

Loading preview...

Model Overview

Biomistral-Clown-Slerp is a 7 billion parameter language model developed by arcee-ai. This model is a product of merging two distinct base models: BioMistral/BioMistral-7B and CorticalStack/pastiche-crown-clown-7b-dare-dpo. The merge was performed using the slerp (spherical linear interpolation) method via mergekit.

Key Characteristics

  • Merged Architecture: Combines the strengths and characteristics of BioMistral-7B and pastiche-crown-clown-7b-dare-dpo.
  • Slerp Merge Method: Utilizes spherical linear interpolation for combining model weights, which can lead to a balanced integration of features from the constituent models.
  • Parameter Configuration: Specific t values were applied during the merge, with different interpolation ratios for self-attention (self_attn) and multi-layer perceptron (mlp) layers, indicating a fine-tuned approach to weight blending.

Potential Use Cases

This model is suitable for applications that can benefit from the combined capabilities of its base models. Developers looking for a model with a unique blend of characteristics derived from BioMistral's potential domain-specific knowledge and the general language understanding of the 'pastiche-crown-clown' model may find this merge particularly useful for:

  • General text generation and understanding.
  • Exploratory NLP tasks where a hybrid model's performance is desired.
  • Applications requiring a balance of different model traits.