Exllamav2 quant (exl2 / 3.0 bpw) made with ExLlamaV2 v0.1.3

Other EXL2 quants:

Quant	Model Size	lm_head
2.2	3250 MB	6
2.5	3478 MB	6
3.0	3894 MB	6
3.5	4311 MB	6
3.75	4518 MB	6
4.0	4727 MB	6
4.25	4935 MB	6
5.0	5559 MB	6
6.0	6489 MB	8
6.5	6909 MB	8
8.0	8123 MB	8

"Poppy Porpoise" is a cutting-edge AI roleplay assistant based on the Llama 3 8B model, specializing in crafting unforgettable narrative experiences. With its advanced language capabilities, Poppy expertly immerses users in an interactive and engaging adventure, tailoring each adventure to their individual preferences.

Note: This variant is an attempt to get something closer to 0.72 while maintaining the improvements of 1.30.

: Presets in repo folder.

If you want to use vision functionality: You must use the latest versions of Koboldcpp. And need to load the specified mmproj file: Llava MMProj.

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Nitral-AI/Pp-72xra1
        layer_range: [0, 32]
      - model: Nitral-AI/Poppy-1.35-Phase1
        layer_range: [0, 32]
merge_method: slerp
base_model: Nitral-AI/Pp-72xra1
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