Daisuke-GGUF

Daisuke

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

Merge Details

Author's Comments

How does Shotmisser64 use Daisuke.

Use alpaca, pyg instruct is not recommended. I use (https://files.catbox.moe/61zzg9.json) along with minimalist context template. Use novel style, mainly because of Erebus. Markdown untested. Use this as an RP assistant. Thanks to pyg, it can also act as 'human' if you want to play as their narrator. You have to edit the response if things go sour at the start. Like Kayra, your config matters a lot, but after 3 turns, it should get better. Feel free to even disable the instruct. Because of Pyg, I recommend putting -3 bias on [376] token (" token) in Kcpp/ST logit bias. It is to reduce pyg's dialogue spam. Since there's another form of (" token), set bias to -100 or ban the token [1346]. As for the [525] (') token, I set it to -5 to reduce 'thinking' done by the character while not banning it outright for words that are using it. I set my Temperature at 1.2 and min p at 0.1. Feel free to play around with other sampler as you see fit.

Special thanks to PygmalionAI for Pygmalion, Jaxxks for Estopia, and Seeker for Erebus, along with the other model creator's model that's being used in the merge.

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• PygmalionAI/pygmalion-2-13b
• output/Estopia_Eru

Configuration

The following YAML configuration was used to produce this model:

merge_method: task_arithmetic
base_model: TheBloke/Llama-2-13B-fp16
models:
  - model: TheBloke/Llama-2-13B-fp16
  - model: Undi95/UtopiaXL-13B
    parameters:
      weight: 1.0
  - model: Doctor-Shotgun/cat-v1.0-13b
    parameters:
      weight: 0.02
  - model: PygmalionAI/mythalion-13b
    parameters:
      weight: 0.10
  - model: Undi95/Emerhyst-13B
    parameters:
      weight: 0.05
  - model: CalderaAI/13B-Thorns-l2
    parameters:
      weight: 0.05
  - model: KoboldAI/LLaMA2-13B-Tiefighter
    parameters:
      weight: 0.20
dtype: float16
name: EstopiaV9 # 1rstSamurai 
---
merge_method: task_arithmetic
base_model: TheBloke/Llama-2-13B-fp16
models:
  - model: TheBloke/Llama-2-13B-fp16
  - model: Undi95/UtopiaXL-13B
    parameters:
      weight: 1.0
  - model: Doctor-Shotgun/cat-v1.0-13b
    parameters:
      weight: 0.01
  - model: chargoddard/rpguild-chatml-13b
    parameters:
      weight: 0.02
  - model: PygmalionAI/mythalion-13b
    parameters:
      weight: 0.08
  - model: CalderaAI/13B-Thorns-l2
    parameters:
      weight: 0.02
  - model: KoboldAI/LLaMA2-13B-Tiefighter
    parameters:
      weight: 0.20
dtype: float16
name: EstopiaV13 # No13
---
models:
  - model: output/EstopiaV9
    parameters:
      weight: 1
      density: 1
  - model: output/EstopiaV13
    parameters:
      weight: 0.05
      density: 0.30
merge_method: dare_ties
base_model: TheBloke/Llama-2-13B-fp16
parameters:
  int8_mask: true
dtype: bfloat16
name: Estopia_Dare # rainbowrainbow 
---
models:
  - model: output/Estopia_Dare
    parameters:
      weight: 1
      density: 1
  - model: /home/mixer/koboldai/models/llama2-13b-erebus-v3
    parameters:
      weight: 0.2
      density: 0.1
merge_method: dare_ties
base_model: TheBloke/Llama-2-13B-fp16
parameters:
  int8_mask: true
dtype: bfloat16
name: Estopia_Eru # A-JAX
---
# From the top to Estopia_Eru is by Jaxxks, I just stack Estopia_Eru with Pyg2 to give it Pyg's dialogue capability. 
slices:
  - sources:
    - model: output/Estopia_Eru
      layer_range: [0, 16]
  - sources:
    - model: PygmalionAI/pygmalion-2-13b
      layer_range: [8, 24]
  - sources:
    - model: output/Estopia_Eru
      layer_range: [17, 32]
  - sources:
    - model: PygmalionAI/pygmalion-2-13b
      layer_range: [25, 40]
merge_method: passthrough
dtype: float16