RichardErkhov/Inv_-_Konstanta-V4-Alpha-7B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Konstanta-V4-Alpha-7B - GGUF

• —Model creator: https://huggingface.co/Inv/
• —Original model: https://huggingface.co/Inv/Konstanta-V4-Alpha-7B/

Original model description: --- base_model:

• —Inv/Konstanta-7B library_name: transformers tags:
• —mergekit
• —merge
• —senseable/WestLake-7B-v2
• —KatyTheCutie/LemonadeRP-4.5.3
• —roleplay
• —rp license: apache-2.0 ---

Konstanta-V4-Alpha-7B

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

Alright, so, this model seems to be REALLY good. Konstanta-7B is pretty good either, but this one is still marginally better.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Inv/Konstanta-7B as a base.

Models Merged

The following models were included in the merge:

• —senseable/WestLake-7B-v2
• —KatyTheCutie/LemonadeRP-4.5.3

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
dtype: bfloat16
parameters:
  int8_mask: true
base_model: Inv/Konstanta-7B
models:
  - model: Inv/Konstanta-7B
  - model: KatyTheCutie/LemonadeRP-4.5.3
    parameters:
      density: 0.65
      weight: [0.65, 0.40, 0.35, 0.30, 0.35, 0.40, 0.25]
  - model: senseable/WestLake-7B-v2
    parameters:
      density: 0.85
      weight: [0.25, 0.40, 0.35, 0.30, 0.35, 0.40, 0.65]