Llama-3.3-70B-EveningMirai-Moonwalker

Creative Model

View on Hugging FaceBack to Models

Hourly Usage

Performance Metrics

Avg. Total Time

49.65s

Avg. TTFT

49.19s

Avg. Prefill TPS

3.67

Avg. Gen TPS

20.81

Model Information

Context Size

32768

Quantization

r64

Engine

aphrodite

Creation Method

Merge

Model Type

Llama70B

Chat Template

Llama 3

Reasoning

No

Vision

No

Parameters

70B

Added At

6/23/2025

base_model:

  • KaraKaraWitch/oiiaioiiai-B
  • ReadyArt/Forgotten-Safeword-70B-v5.0
  • Delta-Vector/Austral-70B-Preview
  • KaraKaraWitch/Llama-EveningMirai-3.3-70B library_name: transformers tags:
  • mergekit
  • merge

EveningMoonWalker

This is a merge of pre-trained language models created using mergekit.

Model Vibes

...Not entirely feeling it with this one:

  • Feels more "insane" in a bad way.
    • I think pulling in thinking caused the model to be more braindamaged.
    • Might need another approach to this TBH. I wanna try model stock next atually.

Merge Details

Merge Method

This model was merged using the SCE merge method using ReadyArt/Forgotten-Safeword-70B-v5.0 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: KaraKaraWitch/oiiaioiiai-B
  - model: KaraKaraWitch/Llama-EveningMirai-3.3-70B
  - model: Delta-Vector/Austral-70B-Preview

merge_method: sce
base_model: ReadyArt/Forgotten-Safeword-70B-v5.0
parameters:
  normalize: true
dtype: bfloat16