Model Overview

pabloce/Dolphin-2.8-slerp is a 7 billion parameter language model resulting from a merge of two pre-trained models: yam-peleg/Experiment26-7B and cognitivecomputations/dolphin-2.8-experiment26-7b. This merge was performed using the SLERP (Spherical Linear Interpolation) method, a technique often employed to combine the strengths of different models while maintaining coherence.

Merge Details

• Method: SLERP (Spherical Linear Interpolation)
• Constituent Models:
  • yam-peleg/Experiment26-7B
  • cognitivecomputations/dolphin-2.8-experiment26-7b
• Configuration: The merge specifically applied varying interpolation values across different layers and components (self_attn, mlp) of the models, indicating an attempt to fine-tune the contribution of each base model to specific functionalities.

Potential Use Cases

Given its origin as a merge of general-purpose language models, Dolphin-2.8-slerp is likely suitable for a range of applications, including:

• Text generation
• Question answering
• Summarization
• Chatbot development