TareksLab/UL3.3-FUSION-BASE-70B

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 meta-llama/Llama-3.3-70B-Instruct as a base.

Models Merged

The following models were included in the merge:

• TareksLab/UL3.3-Nemo-X80-BASE-70B
• TareksLab/UL3.3-Hermes-X80-BASE-70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TareksLab/UL3.3-Hermes-X80-BASE-70B
  - model: TareksLab/UL3.3-Nemo-X80-BASE-70B
base_model: meta-llama/Llama-3.3-70B-Instruct
merge_method: model_stock
chat_template: llama3
dtype: float32
out_dtype: bfloat16
tokenizer:
 source: TareksLab/UL3.3-Nemo-X80-BASE-70B