Cas-Archive/L3-Umbral-Mind-RP-v0.1-8B

merge

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

Merge Details

The goal of this merge was to make an RP model better suited for role-plays with heavy themes such as but not limited to:

• Mental illness
• Self-harm
• Trauma
• Suicide

I hated how RP models tended to be overly positive and hopeful with role-plays involving such themes, but thanks to failspy/Llama-3-8B-Instruct-MopeyMule this problem has been lessened considerably.

I haven't done extensive testing yet, but the bit of testing I did do has shown noticeably good results in lessening how positive the bot is in its writing style.

If you're an enjoyer of savior/reverse savior type role-plays like myself, then this bot is for you.

Merge Method

This model was merged using several Task Arithmetic merges and then tied together with a Model Stock merge.

Models Merged

The following models were included in the merge:

• Casual-Autopsy/Umbral-1

  • Sao10K/L3-8B-Stheno-v3.2
  • failspy/Llama-3-8B-Instruct-MopeyMule

• Casual-Autopsy/Umbral-2

  • Hastagaras/Jamet-8B-L3-MK.V-Blackroot
  • failspy/Llama-3-8B-Instruct-MopeyMule

• Casual-Autopsy/Umbral-3

  • grimjim/Llama-3-Oasis-v1-OAS-8B
  • failspy/Llama-3-8B-Instruct-MopeyMule

Secret Sauce

The following YAML configurations were used to produce this model:

Umbral-1

slices:
- sources:
  - model: Sao10K/L3-8B-Stheno-v3.2
    layer_range: [0, 32]
  - model: failspy/Llama-3-8B-Instruct-MopeyMule
    layer_range: [0, 32]
    parameters:
      weight: 0.25
merge_method: task_arithmetic
base_model: Sao10K/L3-8B-Stheno-v3.2
dtype: bfloat16

Umbral-2

slices:
- sources:
  - model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
    layer_range: [0, 32]
  - model: failspy/Llama-3-8B-Instruct-MopeyMule
    layer_range: [0, 32]
    parameters:
      weight: 0.15
merge_method: task_arithmetic
base_model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
dtype: bfloat16

Umbral-3

slices:
- sources:
  - model: grimjim/Llama-3-Oasis-v1-OAS-8B
    layer_range: [0, 32]
  - model: failspy/Llama-3-8B-Instruct-MopeyMule
    layer_range: [0, 32]
    parameters:
      weight: 0.35
merge_method: task_arithmetic
base_model: grimjim/Llama-3-Oasis-v1-OAS-8B
dtype: bfloat16

Umbral-Mind-RP-8B

models:
  - model: Casual-Autopsy/Umbral-1
  - model: Casual-Autopsy/Umbral-2
  - model: Casual-Autopsy/Umbral-3
merge_method: model_stock
base_model: Casual-Autopsy/Umbral-1
dtype: bfloat16