SeaMax-7B-exl2-4bpw

This is an ExLlamaV2 quantized model in 4bpw of mpasila/SeaMax-7B using the default calibration dataset.

Original Model card:

SeaMax-7B

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 mpasila/PIPPA-Named-7B as a base.

Models Merged

The following models were included in the merge:

• Locutusque/SlimHercules-4.0-Mistral-7B-v0.2
• cognitivecomputations/dolphin-2.8-mistral-7b-v02

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: Locutusque/SlimHercules-4.0-Mistral-7B-v0.2
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
merge_method: ties
base_model: mpasila/PIPPA-Named-7B
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16