CoolFace
Modelpublic

gaverfraxz/Meta-Llama-3.1-8B-Instruct-HalfAbliterated-TIES

sourceHugging Facellama3.1updated 2y agoView on Hugging Face
1likes51downloads
Model Card

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

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 meta-llama/Meta-Llama-3.1-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml
base_model: meta-llama/Meta-Llama-3.1-8B
chat_template: auto
dtype: float16
merge_method: ties
models:
- model: mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
  parameters:
    density: 0.5
    weight: 0.5
- model: meta-llama/Meta-Llama-3.1-8B-Instruct
  parameters:
    density: 0.5
    weight: 0.5
parameters:
  int8_mask: true
  normalize: false

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

MetricValue
Avg.20.77
IFEval (0-Shot)45.51
BBH (3-Shot)28.91
MATH Lvl 5 (4-Shot)11.63
GPQA (0-shot)2.24
MuSR (0-shot)6.59
MMLU-PRO (5-shot)29.76