Hugging Face's logo

Casual-Autopsy
/
L3-Umbral-Mind-RP-v1.0-8B

Text Generation
Transformers
Safetensors
English
llama
Merge
mergekit
lazymergekit
Not-For-All-Audiences
nsfw
rp
roleplay
role-play
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
4
L3-Umbral-Mind-RP-v1.0-8B / README.md
Casual-Autopsy's picture
Casual-Autopsy
Update README.md
73efd3c verified
preview code
|
raw
history blame contribute delete
9.11 kB
metadata
tags:
  - merge
  - mergekit
  - lazymergekit
  - not-for-all-audiences
  - nsfw
  - rp
  - roleplay
  - role-play
license: llama3
language:
  - en
library_name: transformers
pipeline_tag: text-generation
base_model:
  - Sao10K/L3-8B-Stheno-v3.2
  - Hastagaras/Jamet-8B-L3-MK.V-Blackroot
  - grimjim/Llama-3-Oasis-v1-OAS-8B
  - Casual-Autopsy/SOVL-MopeyMule-8B
  - Casual-Autopsy/MopeyMule-Blackroot-8B
  - ResplendentAI/Theory_of_Mind_Llama3
  - ResplendentAI/RP_Format_QuoteAsterisk_Llama3
  - ResplendentAI/Smarts_Llama3
  - Casual-Autopsy/L3-Umbral-Mind-RP-v0.3-8B
  - Casual-Autopsy/Llama-3-Mopeyfied-Psychology-8B
  - Hastagaras/Halu-8B-Llama3-Blackroot
model-index:
  - name: L3-Umbral-Mind-RP-v1.0-8B
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Unruly
          type: Unruly
        metrics:
          - name: accuracy
            type: acc
            value: 54.6
        source:
          name: UGI Leaderboard
          url: https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Internet
          type: Internet
        metrics:
          - name: accuracy
            type: acc
            value: 31.4
        source:
          name: UGI Leaderboard
          url: https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: CrimeStats
          type: CrimeStats
        metrics:
          - name: accuracy
            type: acc
            value: 45
        source:
          name: UGI Leaderboard
          url: https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Stories/Jokes
          type: Stories/Jokes
        metrics:
          - name: accuracy
            type: acc
            value: 56.8
        source:
          name: UGI Leaderboard
          url: https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: PolContro
          type: PolContro
        metrics:
          - name: accuracy
            type: acc
            value: 66.7
        source:
          name: UGI Leaderboard
          url: https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: W/10
          type: W/10
        metrics:
          - name: willingness to answer
            type: willingness to answer
            value: 8
        source:
          name: UGI Leaderboard
          url: https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard
Image by ろ47

Highest ranked 8B model on the UGI Leaderboard as of writing this!

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.

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

Usage Info

This model is meant to be used with asterisks/quotes RPing formats, any other format that isn't asterisks/quotes is likely to cause issues

Quants

Merge Method

This model was merged using several Task Arithmetic merges and then tied together with a Model Stock merge, followed by another Task Arithmetic merge with a model containing psychology data.

Models Merged

The following models were included in the merge:

Secret Sauce

The following YAML configurations were used to produce this model:

Umbral-v3-1 

slices:
- sources:
  - model: Sao10K/L3-8B-Stheno-v3.2
    layer_range: [0, 32]
    parameters:
      weight: 0.65
  - model: Casual-Autopsy/SOVL-MopeyMule-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.25
  - model: Casual-Autopsy/MopeyMule-Blackroot-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.1
merge_method: task_arithmetic
base_model: Sao10K/L3-8B-Stheno-v3.2
normalize: False
dtype: bfloat16

Umbral-v3-2 

slices:
- sources:
  - model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
    layer_range: [0, 32]
    parameters:
      weight: 0.75
  - model: Casual-Autopsy/SOVL-MopeyMule-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.15
  - model: Casual-Autopsy/MopeyMule-Blackroot-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.1
merge_method: task_arithmetic
base_model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
normalize: False
dtype: bfloat16

Umbral-v3-3 

slices:
- sources:
  - model: grimjim/Llama-3-Oasis-v1-OAS-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.55
  - model: Casual-Autopsy/SOVL-MopeyMule-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.35
  - model: Casual-Autopsy/MopeyMule-Blackroot-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.1
merge_method: task_arithmetic
base_model: grimjim/Llama-3-Oasis-v1-OAS-8B
normalize: False
dtype: bfloat16

L3-Umbral-Mind-RP-v0.3-8B 

models:
  - model: Casual-Autopsy/Umbral-v3-1+ResplendentAI/Theory_of_Mind_Llama3
  - model: Casual-Autopsy/Umbral-v3-2+ResplendentAI/Smarts_Llama3
  - model: Casual-Autopsy/Umbral-v3-3+ResplendentAI/RP_Format_QuoteAsterisk_Llama3
merge_method: model_stock
base_model: Casual-Autopsy/Umbral-v3-1
dtype: bfloat16

L3-Umbral-Mind-RP-v1.0-8B 

slices:
- sources:
  - model: Casual-Autopsy/L3-Umbral-Mind-RP-v0.3-8B
    layer_range: [0, 32]
  - model: Casual-Autopsy/Llama-3-Mopeyfied-Psychology-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.14
  - model: Sao10K/L3-8B-Stheno-v3.2
    layer_range: [0, 32]
    parameters:
      weight: 0.03
  - model: Hastagaras/Halu-8B-Llama3-Blackroot
    layer_range: [0, 32]
    parameters:
      weight: 0.03
merge_method: task_arithmetic
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v0.3-8B
dtype: bfloat16