Modelpublic

theocolf/Vora-X-10B

sourceHugging Faceupdated 3mo agoView on Hugging Face

0likes185downloads

Model Card

Vora-X-10B

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:

—theocolf/Vora-X-8B
—NousResearch/Meta-Llama-3-8B

Configuration

The following YAML configuration was used to produce this model:

yaml

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range:
    - 0
    - 20
    model: theocolf/Vora-X-8B
- sources:
  - layer_range:
    - 12
    - 32
    model: NousResearch/Meta-Llama-3-8B