marcuscedricridia/Talon-DEVRELEASE2

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using unsloth/Llama-3.2-3B-Instruct as a base.

Models Merged

The following models were included in the merge:

• unsloth/Llama-3.2-3B-Instruct + marcuscedricridia/talonp4
• unsloth/Llama-3.2-3B-Instruct + marcuscedricridia/talonp10-safe
• unsloth/Llama-3.2-3B-Instruct + marcuscedricridia/talonp8-code.1nemotron
• unsloth/Llama-3.2-3B-Instruct + marcuscedricridia/talonp1lora
• unsloth/Llama-3.2-3B-Instruct + marcuscedricridia/talonp6-mathv1nemotron
• unsloth/Llama-3.2-3B-Instruct + marcuscedricridia/talonp12-helpsteer
• unsloth/Llama-3.2-3B-Instruct + marcuscedricridia/talonp5
• unsloth/Llama-3.2-3B-Instruct + marcuscedricridia/talonp13-debug
• unsloth/Llama-3.2-3B-Instruct + marcuscedricridia/talonp2lora
• unsloth/Llama-3.2-3B-Instruct + marcuscedricridia/talonp7-mathv1.1nemotron
• unsloth/Llama-3.2-3B-Instruct + marcuscedricridia/talon-merged-run1
• unsloth/Llama-3.2-3B-Instruct + marcuscedricridia/talonp11-fleschprose
• unsloth/Llama-3.2-3B-Instruct + marcuscedricridia/talonp9-scinemotron

Configuration

The following YAML configuration was used to produce this model:

merge_method: ties
base_model: unsloth/Llama-3.2-3B-Instruct
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16

models:
  - model: unsloth/Llama-3.2-3B-Instruct
    # No parameters needed for the base model itself in this list format

  - model: unsloth/Llama-3.2-3B-Instruct+marcuscedricridia/talon-merged-run1
    parameters:
      density: 0.5
      weight: 0.0461538462

  - model: unsloth/Llama-3.2-3B-Instruct+marcuscedricridia/talonp13-debug
    parameters:
      density: 0.5
      weight: 0.1

  - model: unsloth/Llama-3.2-3B-Instruct+marcuscedricridia/talonp12-helpsteer
    parameters:
      density: 0.5
      weight: 0.0461538462

  - model: unsloth/Llama-3.2-3B-Instruct+marcuscedricridia/talonp11-fleschprose
    parameters:
      density: 0.5
      weight: 0.0461538462

  - model: unsloth/Llama-3.2-3B-Instruct+marcuscedricridia/talonp10-safe
    parameters:
      density: 0.5
      weight: 0.1

  - model: unsloth/Llama-3.2-3B-Instruct+marcuscedricridia/talonp9-scinemotron
    parameters:
      density: 0.5
      weight: 0.1

  - model: unsloth/Llama-3.2-3B-Instruct+marcuscedricridia/talonp8-code.1nemotron
    parameters:
      density: 0.5
      weight: 0.1

  - model: unsloth/Llama-3.2-3B-Instruct+marcuscedricridia/talonp7-mathv1.1nemotron
    parameters:
      density: 0.5
      weight: 0.1

  - model: unsloth/Llama-3.2-3B-Instruct+marcuscedricridia/talonp6-mathv1nemotron
    parameters:
      density: 0.5
      weight: 0.0461538462

  - model: unsloth/Llama-3.2-3B-Instruct+marcuscedricridia/talonp5
    parameters:
      density: 0.5
      weight: 0.0461538462

  - model: unsloth/Llama-3.2-3B-Instruct+marcuscedricridia/talonp4
    parameters:
      density: 0.5
      weight: 0.0461538462

  - model: unsloth/Llama-3.2-3B-Instruct+marcuscedricridia/talonp1lora
    parameters:
      density: 0.5
      weight: 0.1

  - model: unsloth/Llama-3.2-3B-Instruct+marcuscedricridia/talonp2lora
    parameters:
      density: 0.5
      weight: 0.1