Tarek07/Thalassic-Delta-LLaMa-70B

I messed around with the the ingredients in the Thalassic series, essentially testing how much of an effect the base and pivot models had on the merge. In my opinion, this is the best of the Thalassic models.

merge

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

Merge Details

Merge Method

This model was merged using the SCE merge method using SicariusSicariiStuff/Negative_LLAMA_70B as a base.

Models Merged

The following models were included in the merge:

• TheDrummer/Anubis-70B-v1
• EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
• Sao10K/70B-L3.3-Cirrus-x1
• Sao10K/L3.1-70B-Hanami-x1
• deepseek-ai/DeepSeek-R1-Distill-Llama-70B

Configuration

The following YAML configuration was used to produce this model:

models:
  # Pivot model
  - model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
  # Target models
  - model: Sao10K/70B-L3.3-Cirrus-x1
  - model: Sao10K/L3.1-70B-Hanami-x1
  - model: TheDrummer/Anubis-70B-v1
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
merge_method: sce
base_model: SicariusSicariiStuff/Negative_LLAMA_70B
parameters:
  select_topk: 1.0
dtype: bfloat16