RichardErkhov/ChaoticNeutrals_-_Eris_Remix_7B-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Eris_Remix_7B - bnb 4bits

• Model creator: https://huggingface.co/ChaoticNeutrals/
• Original model: https://huggingface.co/ChaoticNeutrals/Eris_Remix_7B/

Original model description:

base_model: [] library_name: transformers tags: - mergekit - merge license: other language: - en

Remix

Quants Thanks to Lewdiculus: https://huggingface.co/Lewdiculous/Eris_Remix_7B-GGUF-IQ-Imatrix

Exl2 bpw here: https://huggingface.co/Test157t/ChaoticNeutrals-Eris_Remix_7B-exl2-5bpw

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: SpecialEdition
        layer_range: [0, 32]
      - model: Remix
        layer_range: [0, 32]
merge_method: slerp
base_model: SpecialEdition
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