infinite-lemonade-SLERP-7B-8bpw-h8-exl2

<br/><br/> 8bpw/h8 exl2 quantization of grimjim/infinite-lemonade-SLERP-7B using default exllamav2 calibration dataset.

---

ORIGINAL CARD:

infinite-lemonade-SLERP-7B

This is a straightforward merge of two RP-oriented models.

Also available as a Q8_0 GGUF quant.

Lightly tested with Alpaca format prompts, temperature 1, and minP 0.01. Although the model claims to have a 32K context window, I would expect degradation once 8-9K is exceeded.

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:

• Endevor/InfinityRP-v1-7B
• KatyTheCutie/LemonadeRP-4.5.3

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Endevor/InfinityRP-v1-7B
        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