arcee-ai/MistralProSupportSlerp

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

MistralProSupportSlerp is a 7 billion parameter language model created by arcee-ai, formed by merging TencentARC/Mistral_Pro_8B_v0.1 and mistralai/Mistral-7B-v0.1+predibase/customer_support using the slerp method. This model is specifically designed to enhance customer support interactions, leveraging the strengths of its constituent models. It offers a 4096-token context length, making it suitable for processing moderate lengths of conversational data.

Loading preview...

Model Overview

arcee-ai/MistralProSupportSlerp is a 7 billion parameter language model developed by arcee-ai. It is a merged model, combining the capabilities of two distinct base models: TencentARC/Mistral_Pro_8B_v0.1 and mistralai/Mistral-7B-v0.1+predibase/customer_support. The merge was performed using the slerp (spherical linear interpolation) method via mergekit.

Key Capabilities

  • Enhanced Customer Support: By integrating a model specifically fine-tuned for customer support, MistralProSupportSlerp is optimized for handling customer service dialogues and related tasks.
  • Hybrid Performance: Leverages the general language understanding and generation capabilities of Mistral_Pro_8B_v0.1 combined with the specialized domain knowledge from the customer support model.
  • Mergekit Configuration: The model's architecture is a result of a specific mergekit configuration, applying different t values to self-attention and MLP layers during the slerp merge process.

Good For

  • Customer Service Applications: Ideal for chatbots, virtual assistants, and automated response systems in customer support environments.
  • Conversational AI: Suitable for generating human-like responses in interactive support scenarios.
  • Domain-Specific Text Generation: Excels in tasks requiring knowledge and tone relevant to customer interactions.