Llama3-Bouncer

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 huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated as a base.

Models Merged

The following models were included in the merge:

• huihui-ai/Llama-3.1-Nemotron-Nano-8B-v1-abliterated
• WhiteRabbitNeo/Llama-3.1-WhiteRabbitNeo-2-8B
• fdtn-ai/Foundation-Sec-8B

Configuration

The following YAML configuration was used to produce this model:

base_model: huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated
merge_method: ties
models:
- model: huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated
  parameters:
    density: 0.8
    weight: 1.0
  exclude:
  - model.embed_tokens.weight
  - lm_head.weight
- model: huihui-ai/Llama-3.1-Nemotron-Nano-8B-v1-abliterated
  parameters:
    density: 0.5
    weight: 1.0
  exclude:
  - model.embed_tokens.weight
  - lm_head.weight
- model: fdtn-ai/Foundation-Sec-8B
  parameters:
    density: 0.6
    weight: 1.0
  exclude:
  - model.embed_tokens.weight
  - lm_head.weight
- model: WhiteRabbitNeo/Llama-3.1-WhiteRabbitNeo-2-8B
  parameters:
    density: 0.7
    weight: 1.0
  exclude:
  - model.embed_tokens.weight
  - lm_head.weight
dtype: bfloat16