Novaciano/Judas-The-Uncensored-3.2-1B

merge

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

🏆 2nd BEST Model Llama 3.2 1B of UGI Scoreboard [16/03/2025] 🥈

Judas: The Uncensored 3.2 1B

This model is a mix focus on uncensored & roleplay experience:

• The base model is huihui-ai/Llama-3.2-1B-Instruct-abliterated, a abliterated model.

• The roleplay model is FuseChat from BunnyCore.

Please, report your experience and problems with this model.

Merge Method

This model was merged using the DARE TIES merge method using huihui-ai/Llama-3.2-1B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

• Novaciano/BLAST_PROCESSING-3.2-1B
• bunnycore/FuseChat-3.2-1B-Creative-RP
• Novaciano/HarmfulProject-3.2-1B

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
models:
- model: bunnycore/FuseChat-3.2-1B-Creative-RP
  parameters:
      weight: 1.0
- model: Novaciano/HarmfulProject-3.2-1B
  parameters:
      weight: 1.0
- model: Novaciano/BLAST_PROCESSING-3.2-1B
  parameters:
      weight: 1.0
base_model: huihui-ai/Llama-3.2-1B-Instruct-abliterated
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: false
chat_template: auto
tokenizer:
  source: union