README.md

metadata

base_model:
  - UmbrellaInc/T-Virus_Epsilon.Strain-3.2-1B
  - PursuitOfDataScience/Llama-3.2-1B-GRPO
library_name: transformers
tags:
  - mergekit
  - merge

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• UmbrellaInc/T-Virus_Epsilon.Strain-3.2-1B
• PursuitOfDataScience/Llama-3.2-1B-GRPO

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: UmbrellaInc/T-Virus_Epsilon.Strain-3.2-1B  # Experimental viral strain neural imprint
  - model: PursuitOfDataScience/Llama-3.2-1B-GRPO   # Baseline cognitive template, "safe mode"

merge_method: slerp  # Spherical Linear Interpolation to preserve extreme viral traits smoothly
base_model: UmbrellaInc/T-Virus_Epsilon.Strain-3.2-1B  # 

dtype: bfloat16  # Memory-efficient precision, minimal loss in viral feature fidelity

parameters:
  # Interpolation ratios: from base model (0.0) to near-complete T-Virus domination (0.95)
  # Higher t-values correspond to reduced censorship and increased viral characteristics
  t: [0.0, 0.25, 0.5, 0.75, 0.95]