RichardErkhov/Lil-R_-_2_PRYMMAL-ECE-2B-SLERP-V2-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

2_PRYMMAL-ECE-2B-SLERP-V2 - bnb 4bits

• Model creator: https://huggingface.co/Lil-R/
• Original model: https://huggingface.co/Lil-R/2_PRYMMAL-ECE-2B-SLERP-V2/

Original model description:

base_model: - google/gemma-2-2b-it - zake7749/gemma-2-2b-it-chinese-kyara-dpo library_name: transformers tags: - mergekit - merge license: apache-2.0

merged_model

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:

• google/gemma-2-2b-it
• zake7749/gemma-2-2b-it-chinese-kyara-dpo

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: zake7749/gemma-2-2b-it-chinese-kyara-dpo
        layer_range: [0, 26]
      - model: google/gemma-2-2b-it
        layer_range: [0, 26]    
merge_method: slerp
base_model: zake7749/gemma-2-2b-it-chinese-kyara-dpo
parameters:
  t:
    - filter: self_attn
      value: [0, 0.25, 0.5, 0.75, 1]
    - filter: mlp
      value: [1, 0.75, 0.5, 0.25, 0]
    - value: 0.5
dtype: bfloat16