Natkituwu/IceLemonTeaRP-32k-7b-7.1bpw-exl2

IceLemonTeaRP-32k-7b-8.0bpw-h6-exl2

7.1bpw-exl2 quant of icefog72/IceLemonTeaRP-32k-7b

Tested 16k context at 4bit cache max for windows and 32k context at 4bit cache max for linux (RTX 4060 8GB)

perfect for 8GB VRAM users that want as much quality as possible with alot of context.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• Kunokukulemonchini-32k-7b
• Mixtral_AI_Cyber_3.m1-BigL

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Mixtral_AI_Cyber_3.m1-BigL
        layer_range: [0, 32]
      - model: Kunokukulemonchini-32k-7b
        layer_range: [0, 32]
merge_method: slerp
base_model: Kunokukulemonchini-32k-7b
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: float16