kukulemon-7B-8.0bpw_h8_exl2

kukulemon-7B-8.0bpw-h8_exl2

This is an 8.0bpw h8 exl2 quant of a merger of two similar models with strong reasoning, hopefully resulting in "dense" encoding of said reasoning, was merged with a model targeting roleplay.

I've tested with ChatML prompts with temperature=1.1 and minP=0.03. The model itself supports Alpaca format prompts. The model claims a context length of 32K, but I found it lost coherence after 8K in informal testing. I prefer to stick with 8.0bpw h8 exl2 or Q8_0 GGUF for maximum coherence.

Alternative downloads:

• iMatrix GGUF quants courtesy of Lewdiculous
• fp16 safetensors
• GGUF quants

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:

• grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B
• KatyTheCutie/LemonadeRP-4.5.3

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B
        layer_range: [0, 32]
      - model: KatyTheCutie/LemonadeRP-4.5.3
        layer_range: [0, 32]
# or, the equivalent models: syntax:
# models:
merge_method: slerp
base_model: KatyTheCutie/LemonadeRP-4.5.3
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 # fallback for rest of tensors
dtype: float16