NexesMess/Llama_3.x_70b_SmarTricks_v1.55_Karcher

merge

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

Merge Details

Merge Method

This model was merged using the Karcher Mean merge method using huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated as a base.

Models Merged

The following models were included in the merge:

• SicariusSicariiStuff/Negative_LLAMA_70B
• NousResearch/Hermes-3-Llama-3.1-70B
• hitachi-nlp/Llama-3.1-70B-FLDx2
• migtissera/Tess-3-Llama-3.1-70B
• TheDrummer/Fallen-Llama-3.3-R1-70B-v1

Configuration

The following YAML configuration was used to produce this model:

merge_method: karcher
models:
  - model: huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
  - model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
  - model: NousResearch/Hermes-3-Llama-3.1-70B
  - model: migtissera/Tess-3-Llama-3.1-70B
  - model: hitachi-nlp/Llama-3.1-70B-FLDx2
base_model: huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  filter_wise: false
  max_iter: 10
  tol: 1e-5
chat_template: auto
tokenizer:
  source: union
name: Llama_3.x_70b_SmarTricks_v1.55_Karcher