Nexesenex/Llama_3.x_70b_Tristar_V2.1

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Nexesenex/Llama_3.x_70b_SmarTrident_v1.02 as a base.

Models Merged

The following models were included in the merge:

• NexesMess/Llama_3.3_70b_FallenDonkey
• NexesMess/Llama_3.x_70b_Catalina

Configuration

The following YAML configuration was used to produce this model:

merge_method: model_stock
models:
  - model: NexesMess/Llama_3.x_70b_Catalina
    parameters:
      weight: 1.0
  - model: NexesMess/Llama_3.3_70b_FallenDonkey
    parameters:
      weight: 1.0
base_model: Nexesenex/Llama_3.x_70b_SmarTrident_v1.02
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: false
  rescale: false
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union