Masterjp123/NeuralMaid-7b

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:4kTool Calling:SupportedPublished:Jan 6, 2024License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Masterjp123/NeuralMaid-7b is a 7 billion parameter language model created by Masterjp123 through a merge of NurtureAI/neural-chat-7b-v3-16k and NeverSleep/Noromaid-7b-v0.2 using the SLERP method. This model combines characteristics from its base models, offering a 4096 token context length. It is designed as a general-purpose merged model, leveraging the strengths of its components.

Loading preview...

Masterjp123/NeuralMaid-7b: A Merged Language Model

Masterjp123/NeuralMaid-7b is a 7 billion parameter language model resulting from a merge of two pre-trained models: NurtureAI/neural-chat-7b-v3-16k and NeverSleep/Noromaid-7b-v0.2. This model was created using the SLERP merge method via the MergeKit tool.

Key Characteristics

  • Architecture: A 7B parameter model, inheriting its base architecture from the merged components.
  • Context Length: Supports a context window of 4096 tokens.
  • Merge Method: Utilizes the Spherical Linear Interpolation (SLERP) method for combining model weights, specifically applying different interpolation ratios to self-attention and MLP layers.
  • Component Models: Integrates features from both neural-chat-7b-v3-16k (known for its instruction-following capabilities and larger context) and Noromaid-7b-v0.2.

Intended Use

This model is suitable for general language generation tasks, leveraging the combined strengths of its constituent models. Developers can explore its performance across various NLP applications where a 7B parameter model with a 4k context window is appropriate.