Llama-3.X-Workout-70B

Name: Llama-3.X-Workout-70B
Availability: InStock

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

Doomer but probably Gooder. Rest of the numbers are guessed up.

This will probably be the last model I bad mix for a while. Going to touch grass in another country.

Merge Details

Merge Method

This model was merged using the TIES merge method using SicariusSicariiStuff/Negative_LLAMA_70B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: Blackroot/Mirai-3.0-70B
    parameters:
      density: 0.2
      weight: 0.5
  - model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
    parameters:
      density: 1
      weight: 0.25
  - model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
    parameters:
      density: 0.3
      weight: 0.5
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
    parameters:
      density: 0.75
      weight: 0.5
  - model: TheDrummer/Anubis-70B-v1
    parameters:
      density: 0.351
      weight: 0.751
  - model: Sao10K/L3.3-70B-Euryale-v2.3
    parameters:
      density: 0.420
      weight: 0.679
  - model: Sao10K/70B-L3.3-Cirrus-x1
    parameters:
      density: 0.43
      weight: 0.3
  - model: nitky/Llama-3.3-SuperSwallowX-70B-Instruct-v0.1
    parameters:
      density: 0.25
      weight: 0.2
  - model: Undi95/Sushi-v1.4
    parameters:
      density: 0.1457
      weight: 0.69
  - model: pankajmathur/orca_mini_v9_3_70B
    parameters:
      density: 0.2
      weight: 0.2

merge_method: ties
base_model: SicariusSicariiStuff/Negative_LLAMA_70B
parameters:
  normalize: true
dtype: bfloat16

KaraKaraModel/Llama-3.X-Workout-70B

Llama-3.X-Workout-70B

Merge Details

Merge Method

Models Merged

Configuration

KaraKaraModel/
Llama-3.X-Workout-70B