Modelpublic

BruhzWater/Apocrypha-L3.3-70b-0.3

sourceHugging Faceupdated 1y agoView on Hugging Face

1likes23downloads

Model Card

Apocrypha-L3.3-70b-0.3

image/png

Creative Writing and Storytelling model. 2/3 stage merge

Sampler settings to start with: - Temp: 0.95 - 1

Min P: 0.015 - 0.02

Chat and Instruct Template: - Llama3

Merge Details

Merge Method

This model was merged using the SCE merge method using bruhzair--prototype-0.4x257 as a base.

Base details: https://huggingface.co/BruhzWater/Eden-L3.3-70b-0.3

Models Merged

The following models were included in the merge:

—nbeerbower--Llama3.1-Gutenberg-Doppel-70B (extra ancient book sauce)
—Doctor-Shotgun--L3.3-70B-Magnum-Diamond (divine horny prose sauce)
—TheDrummer--Fallen-Llama-3.3-70B-v1 (big bad mean sauce)
—tdrussell--Llama-3-70B-Instruct-Storywriter (uber premium story sauce)
—EVA-UNIT-01--EVA-LLaMA-3.33-70B-v0.0 (unrivaled epic narrative sauce)

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: /workspace/cache/models--nbeerbower--Llama3.1-Gutenberg-Doppel-70B/snapshots/f083f3a89b8275e7e5329bb0668ada189f80b507
  - model: /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Diamond/snapshots/a7dfb66b4469a4c9ca07ff28bccc73a44797e76c
  - model: /workspace/cache/models--EVA-UNIT-01--EVA-LLaMA-3.33-70B-v0.0/snapshots/501b61987a44172bf2d68365893fcd13081ad4db
  - model: /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c
  - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8
base_model: /workspace/cache/models--bruhzair--prototype-0.4x257/snapshots/60a848fe9776f453b6f640662ca07493da8c1d12
select_topk: 0.24
merge_method: sce
tokenizer:
  source: base
chat_template: llama3
pad_to_multiple_of: 8
int8_mask: true
dtype: float32