Erosumika-7B-v3

4.0bpw exl2 quant. great for 16k+ context on 6GB GPUS!

Original Model : (https://huggingface.co/localfultonextractor/Erosumika-7B-v3)

Model Details

A DARE TIES merge between Nitral's Kunocchini-7b, Endevor's InfinityRP-v1-7B and my FlatErosAlpha, a flattened(in order to keep the vocab size 32000) version of tavtav's eros-7B-ALPHA. Alpaca and ChatML work best.

GGUF quants

Limitations and biases

The intended use-case for this model is fictional writing for entertainment purposes. Any other sort of usage is out of scope. It may produce socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. Outputs might often be factually wrong or misleading.

base_model: localfultonextractor/FlatErosAlpha
models:
  - model: localfultonextractor/FlatErosAlpha
  - model: Epiculous/InfinityRP-v1-7B
    parameters:
      density: 0.4
      weight: 0.25
  - model: Nitral-AI/Kunocchini-7b
    parameters:
      density: 0.3
      weight: 0.35
merge_method: dare_ties
dtype: bfloat16

Note: Copied the tokenizer from InfinityRP-v1-7B.