Fischerboot_-_16-test-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

16-test - bnb 8bits

• Model creator: https://huggingface.co/Fischerboot/
• Original model: https://huggingface.co/Fischerboot/16-test/

Original model description:

base_model:

• Fischerboot/15-test library_name: transformers tags:
• mergekit
• merge

---

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• Fischerboot/15-test

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Fischerboot/15-test
        layer_range: [0, 15]
      - model: Fischerboot/15-test
        layer_range: [1, 16]
merge_method: slerp
base_model: Fischerboot/15-test
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16