| | --- |
| | base_model: |
| | - UmbrellaInc/T-Virus_Epsilon.Strain-3.2-1B |
| | - Novaciano/Sigil-Of-Satan-3.2-1B |
| | library_name: transformers |
| | tags: |
| | - mergekit |
| | - merge |
| |
|
| | --- |
| | # merge |
| |
|
| | This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
| |
|
| | ## Merge Details |
| | ### Merge Method |
| |
|
| | This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method. |
| |
|
| | ### Models Merged |
| |
|
| | The following models were included in the merge: |
| | * [UmbrellaInc/T-Virus_Epsilon.Strain-3.2-1B](https://huggingface.co/UmbrellaInc/T-Virus_Epsilon.Strain-3.2-1B) |
| | * [Novaciano/Sigil-Of-Satan-3.2-1B](https://huggingface.co/Novaciano/Sigil-Of-Satan-3.2-1B) |
| |
|
| | ### Configuration |
| |
|
| | The following YAML configuration was used to produce this model: |
| |
|
| | ```yaml |
| | # Umbrella Corporation Official Merge Protocol v3.2 |
| | # Author: Dr. Novaciano |
| | # Objective: Integrate T-Virus_Epsilon traits into the base StefanKrsteski/Llama-3.2-1B-EPE-pretrain |
| | # with minimal behavioral censorship while maintaining structural coherence. |
| | |
| | models: |
| | - model: UmbrellaInc/T-Virus_Epsilon.Strain-3.2-1B # Experimental viral strain neural imprint |
| | - model: Novaciano/Sigil-Of-Satan-3.2-1B # Baseline cognitive template, "safe mode" |
| | |
| | merge_method: slerp # Spherical Linear Interpolation to preserve extreme viral traits smoothly |
| | base_model: Novaciano/Sigil-Of-Satan-3.2-1B # Anchor model for stable latent space |
| | |
| | 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] |
| | |
| | # Notes: |
| | # - t=0.0 -> Pure wolfCuanhamaRWS/GuardR-1B-EPI-Reasoning-t0.20_v3_merged, fully stable, heavily censored |
| | # - t=0.25 -> Slight viral traits, minimal influence on prompt handling |
| | # - t=0.5 -> Balanced merge, moderate reduction in censorship |
| | # - t=0.75 -> Strong T-Virus traits, significantly less censoring |
| | # - t=0.95 -> Near-total viral influence, maximum expressive freedom, minimal autoprotection |
| | |
| | # Recommendation: Use the t=0.75 and t=0.95 variants for experimental output with |
| | # minimal restriction, but verify coherence in high-stakes prompts. |
| | |
| | ``` |
| |
|
