README.md

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-merged-one-layer-only - AWQ

• Model creator: https://huggingface.co/choprahetarth/
• Original model: https://huggingface.co/choprahetarth/gemma-merged-one-layer-only/

Original model description:

base_model:

• google/gemma-2-2b
• google/gemma-2-2b-it library_name: transformers tags:
• mergekit
• merge

---

Untitled Model (1)

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 google/gemma-2-2b as a base.

Models Merged

The following models were included in the merge:

• google/gemma-2-2b-it

Configuration

The following YAML configuration was used to produce this model:

base_model: google/gemma-2-2b
dtype: bfloat16
merge_method: ties
parameters:
  int8_mask: 1.0
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 26]
    model: google/gemma-2-2b
  - layer_range: [0, 26]
    model: google/gemma-2-2b-it
    parameters:
      density:
      - filter: self_attn.o_proj.9
        value: 1.0
      - value: 0.001
      weight:
      - value: 1.0
tokenizer_source: union