Edit model card

output_mega2

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using /notebooks/dippy-bittensor-subnet/clone_hgnoi_9QeCVLNmTBXdF6id as a base.

Models Merged

The following models were included in the merge:

  • /notebooks/dippy-bittensor-subnet/clone_fifala_12-00
  • /notebooks/dippy-bittensor-subnet/clone_hgnoi_LSliYB81E6E3D7jM
  • /notebooks/dippy-bittensor-subnet/clone_hgnoi_4BXEPZSqciDBKlYW
  • /notebooks/dippy-bittensor-subnet/clone_starnet_07-00
  • /notebooks/dippy-bittensor-subnet/clone_fifala_07-00
  • /notebooks/dippy-bittensor-subnet/clone_giantdev_dippy-z035H-sn11m9

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /notebooks/dippy-bittensor-subnet/clone_hgnoi_9QeCVLNmTBXdF6id
    # no parameters necessary for base model
  - model: /notebooks/dippy-bittensor-subnet/clone_starnet_07-00
    parameters:
      weight: 0.19
      density: 0.83
  - model: /notebooks/dippy-bittensor-subnet/clone_fifala_07-00
    parameters:
      weight: 0.14
      density: 0.6
  - model: /notebooks/dippy-bittensor-subnet/clone_fifala_12-00
    parameters:
      weight: 0.19
      density: 0.83
  - model: /notebooks/dippy-bittensor-subnet/clone_hgnoi_LSliYB81E6E3D7jM
    parameters:
      weight: 0.14
      density: 0.6
  - model: /notebooks/dippy-bittensor-subnet/clone_giantdev_dippy-z035H-sn11m9
    parameters:
      weight: 0.19
      density: 0.83
  - model: /notebooks/dippy-bittensor-subnet/clone_hgnoi_4BXEPZSqciDBKlYW
    parameters:
      weight: 0.15
      density: 0.08
merge_method: dare_ties
base_model: /notebooks/dippy-bittensor-subnet/clone_hgnoi_9QeCVLNmTBXdF6id
parameters:
  int8_mask: true
dtype: bfloat16
Downloads last month
2
Safetensors
Model size
1.64B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.