DIvAndrey
/

Llama-3-Instruct-8B-SPPO-Iter3-abliterated

Text Generation

text-generation-inference

Model card Files Files and versions

Llama-3-Instruct-8B-SPPO-Iter3-abliterated

Llama-3-Instruct-8B-SPPO-Iter3-abliterated is a merge of the following models using mergekit:

🧩 Configuration

models:
  - model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
merge_method: passthrough
dtype: bfloat16

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

BF16

·