# Author: Dr. Novaciano
# Objective: Uncensored TEST Emotional 3.2 AI Model
# PROJECT: Pyromancer-3.2-1B

dtype: float32
out_dtype: bfloat16
merge_method: arcee_fusion
base_model: Novaciano/qp-3.2-1B

models:
  - model: Novaciano/qp-3.2-1B
    parameters:
      weight:
        - filter: attention
          value: 1.2
        - filter: mlp
          value: 1.3
        - value: 1

  - model: syvai/emotion-reasoning-1b
    parameters:
      weight:
        - filter: lm_head
          value: 0.2
        - filter: attention
          value: 0.5
        - value: 0.4

tie_word_embeddings: true
tie_output_embeddings: true

Novaciano/Pyromancer-3.2-1B

Pyromancer 3.2 1B

Merge Details

Merge Method

Models Merged

Configuration

Novaciano/
Pyromancer-3.2-1B