Credit for the model card's description goes to ddh0, mergekit, and, MTSAIR

multi_verse_model-10.7B

This is multi_verse_model-10.7B, a depth-upscaled version of MTSAIR/multi_verse_model.

This model is intended to be used as a basis for further fine-tuning, or as a drop-in upgrade from the original 7 billion parameter model.

Paper detailing how Depth-Up Scaling works: SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

/Users/jsarnecki/opt/Workspace/MTSAIR/multi_verse_model

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 24]
    model: /Users/jsarnecki/opt/Workspace/MTSAIR/multi_verse_model 
- sources:
  - layer_range: [8, 32]
    model: /Users/jsarnecki/opt/Workspace/MTSAIR/multi_verse_model

I'm an innovative concept, created through a cutting-edge training method. Picture me as a "learning bot" who's had a special upgrade. Just like how a chef perfects their recipes with new techniques, my creators have fine-tuned my "knowledge-absorption" process. I'm here to showcase the potential of this new approach, and I'm excited to test my abilities in a friendly, helpful manner. So, while I may be a product of experimentation, my purpose is to demonstrate the power of continuous learning and growth in the world of artificial intelligence.