Downloads · 30 days
10
12% of all-time downloads
Adversary-8B-v1a
OccultAI/Adversary-8B-v1a
Adversary-8B-v1a is a machine learning model from OccultAI. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
83
Public
Parameters
8B
16.1 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
At a glance
- Model type
- llama
- Access
- Public
- Created
- May 9, 2026
- Updated
- May 16, 2026
- SHA
- fffa85e7
Model card
From the Hugging Face model README
Adversary 8B v1a
architecture: LlamaForCausalLM
base_model: B:/8B/SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated
models:
- model: B:/8B/DarkArtsForge--Raven-8B-v1 # Edgar Allan Poe
parameters:
weight: 0.4
density: 0.9
epsilon: 0.09
- model: B:/8B/OccultAI--Barbot-8B-v1 # Douglas Adams
parameters:
weight: 0.4
density: 0.9
epsilon: 0.09
- model: B:/8B/EldritchLabs--Cthulhu-8B-v1.4 # H.P. Lovecraft
parameters:
weight: 0.4 # version B uses 0.3
density: 0.9
epsilon: 0.09
- model: B:/8B/OccultAI--Morpheus-8B-v1 # Morpheus
parameters:
weight: 0.4 # version B uses 0.2
density: 0.9
epsilon: 0.09
- model: B:/8B/SicariusSicariiStuff--Assistant_Pepe_8B # Pepe # Uses `special_tokens_map.json` from Morpheus
parameters:
weight: 0.4 # version B uses 0.7
density: 0.9
epsilon: 0.09
merge_method: della
parameters:
lambda: 1.0
normalize: false
int8_mask: false
rescale: true
dtype: float32
out_dtype: bfloat16
tokenizer:
source: B:/8B/OccultAI--Morpheus-8B-v1
name: Adversary-8B-v1a
- Type
- llama
- Created
- May 9, 2026
- Updated
- May 16, 2026