gaverfraxz
/

Meta-Llama-3.1-8B-Instruct-HalfAbliterated-DELLA

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Meta-Llama-3.1-8B-Instruct-HalfAbliterated-DELLA

File size: 364 Bytes

bd12a1f

models:
  - model: mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
    parameters:
      weight: 1
  - model: meta-llama/Meta-Llama-3.1-8B-Instruct
    parameters:
      weight: 1
merge_method: della
base_model: meta-llama/Meta-Llama-3.1-8B
parameters:
  normalize: false
  int8_mask: true
  density: 0.7
  lambda: 1.1
  epsilon: 0.25
dtype: float16