merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the TIES merge method using ClaudioItaly/Vangelus-Secundus as a base.
Models Merged
The following models were included in the merge:
- sam-paech/Delirium-v1
- lemon07r/Gemma-2-Ataraxy-v4c-9B
- ClaudioItaly/1800-9B
- sam-paech/Darkest-muse-v1
- sam-paech/Quill-v1
- jsgreenawalt/gemma-2-9B-it-advanced-v2.1
Configuration
The following YAML configuration was used to produce this model:
models:
- model: lemon07r/Gemma-2-Ataraxy-v4c-9B
parameters:
weight: 0.35 # Maggiore peso per competenze specifiche
- model: ClaudioItaly/1800-9B
parameters:
weight: 0.25 # Modello base originale
- model: sam-paech/Delirium-v1
parameters:
weight: 0.15 # Contributo creativo
- model: jsgreenawalt/gemma-2-9B-it-advanced-v2.1
parameters:
weight: 0.15 # Competenze in italiano
- model: sam-paech/Quill-v1
parameters:
weight: 0.05 # Stile narrativo
- model: sam-paech/Darkest-muse-v1
parameters:
weight: 0.05 # Elementi dark/creativi
merge_method: ties
base_model: ClaudioItaly/Vangelus-Secundus
parameters:
density: 0.6 # Migliora la selezione dei parametri rilevanti
normalize: true # Normalizza i pesi per stabilità
int8_mask: true
dtype: bfloat16
# Configurazione aggiuntiva consigliata
tokenizer_source: union # Combina i tokenizer
allow_crimes: false # Previene combinazioni non allineate
experts:
source_model: ClaudioItaly/1800-9B # Esperto primario
positive_prompts: ["analisi tecnica", "creatività", "linguaggio naturale"]
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.