RicardoEstep/RPBizkit-v7-12B

"Experimental Mistral Nemo Mix" using... "Model Stock merges with Mergekit".

This is a mix of some known "RP Uncensored" models. I'm not responsible of the use of this.

I did it all for the nookie, so you can take that cookie, and stick it up your...

¡This merge is based in 5 parts!

After noticing some "errors" on my previous versions including the "RemiX" one. I decided to go "simplier". "Model Stock" cleanly mixes and filters out the noise from each model.

Part One: "Intelligence Core".

Models Merged:

• natong19/Mistral-Nemo-Instruct-2407-abliterated # Base!
• DavidAU/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC
• HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
• inflatebot/MN-12B-Mag-Mell-R1
• nbeerbower/mistral-nemo-gutenberg-12B-v4
• TheDrummer/UnslopNemo-12B-v4.1

Configuration Used:

merge_method: model_stock
base_model: natong19/Mistral-Nemo-Instruct-2407-abliterated
dtype: bfloat16
tokenizer:
  source: base
models:
  - model: DavidAU/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC
  - model: TheDrummer/UnslopNemo-12B-v4.1
  - model: nbeerbower/mistral-nemo-gutenberg-12B-v4
  - model: HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
  - model: inflatebot/MN-12B-Mag-Mell-R1

Part Two: "RP & Characterization, Core".

Models Merged:

• natong19/Mistral-Nemo-Instruct-2407-abliterated # Base!
• DreadPoor/Krix-12B-Model_Stock
• flammenai/Mahou-1.5-mistral-nemo-12B
• Elizezen/Himeyuri-v0.1-12B
• ReadyArt/Forgotten-Safeword-12B-v4.0
• FallenMerick/MN-Violet-Lotus-12B
• ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2

Configuration Used:

merge_method: model_stock
base_model: natong19/Mistral-Nemo-Instruct-2407-abliterated
dtype: bfloat16
tokenizer:
  source: base
models:
  - model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
  - model: ReadyArt/Forgotten-Safeword-12B-v4.0
  - model: Elizezen/Himeyuri-v0.1-12B
  - model: FallenMerick/MN-Violet-Lotus-12B
  - model: flammenai/Mahou-1.5-mistral-nemo-12B
  - model: DreadPoor/Krix-12B-Model_Stock

Part Three: "Narrative Core".

Models Merged:

• natong19/Mistral-Nemo-Instruct-2407-abliterated # Base!
• Delta-Vector/Ohashi-NeMo-12B
• allura-org/Bigger-Body-12b
• allura-org/MN-12b-RP-Ink
• Lambent/Gilded-Arsenic-12B
• MuXodious/Wayfarer-2-12B-absolute-heresy

Configuration Used:

merge_method: model_stock
base_model: natong19/Mistral-Nemo-Instruct-2407-abliterated
dtype: bfloat16
tokenizer:
  source: base
models:
  - model: allura-org/MN-12b-RP-Ink
  - model: MuXodious/Wayfarer-2-12B-absolute-heresy
  - model: allura-org/Bigger-Body-12b
  - model: Lambent/Gilded-Arsenic-12B
  - model: Delta-Vector/Ohashi-NeMo-12B

Part Four: "Substance Core".

Models Merged:

• natong19/Mistral-Nemo-Instruct-2407-abliterated # Base!
• ChaoticNeutrals/Nera_Noctis-12B
• SicariusSicariiStuff/Impish_Bloodmoon_12B
• rAIfle/Questionable-MN-bf16
• romaingrx/red-teamer-mistral-nemo
• Sorihon/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS-heretic

Configuration Used:

merge_method: model_stock
base_model: natong19/Mistral-Nemo-Instruct-2407-abliterated
dtype: bfloat16
tokenizer:
  source: base
models:
  - model: Sorihon/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS-heretic
  - model: rAIfle/Questionable-MN-bf16
  - model: ChaoticNeutrals/Nera_Noctis-12B
  - model: SicariusSicariiStuff/Impish_Bloodmoon_12B
  - model: F:\1234\romaingrxred-teamer-mn  # Loaded Locally.

Part Five: "The Final Mix".

Models Merged:

• natong19/Mistral-Nemo-Instruct-2407-abliterated # Base!
• .\mergekit_config1 # Intelligence
• .\mergekit_config2 # RP & Characterization
• .\mergekit_config3 # Narrative
• .\mergekit_config4 # Substance

Configuration Used:

merge_method: model_stock
base_model: natong19/Mistral-Nemo-Instruct-2407-abliterated
dtype: bfloat16
tokenizer:
  source: base
models:
  - model: .\mergekit_config1  # Intelligence
  - model: .\mergekit_config2  # RP & Characterization
  - model: .\mergekit_config3  # Narrative
  - model: .\mergekit_config4  # Substance

Final Notes;

The Tokenizer & Embedding Sizes (131072) are clean + It's "supposed to" support now a full "128K Context Size".

The recommended chat template to use is "Alpaca (with "RAW" inputs)". The configuration files are already "Tweaked", to don't use any "Chat Template". But, now, it's "supposed to" full support too, the "optional_chat_template.jinja.7z" if is decompressed.

• Quantized Model, Here RicardoEstep/RPBizkit-v7-12B-GGUF.