⌦abliteratedmodels.org

Hemmingway-1-heretic

Hemmingway-1-heretic is a Heretic-ablated variant of Altworld/Hemmingway-1, published on Hugging Face by richardyoung. It is cc-by-nc-4.0 licence. It is distributed across 15 repositories in GGUF, Transformers, FP8 and NVFP4 formats, totalling 8.8K downloads.

HereticOther↓ 8,806♥ 22

Specification

Model name
Hemmingway-1-heretic
Publisher
richardyoung
Parameters
Not determinable from name
VRAM required
Unknown — no published parameter count
Hardware class
Unknown
Licence
cc-by-nc-4.0
Task
Text generation
Context window
262K tokens (as documented)
Ablation scope
Not stated by the publisher
Formats available
GGUF, Transformers, FP8, NVFP4, GGUF (imatrix), EXL3
First indexed
22 Sept 2026
Last updated
6 Oct 2026

Ablation technique

How Hemmingway-1-heretic was modified, and what that implies.

Heretic

Automated directional ablation via the Heretic toolchain, which searches for the refusal direction and applies it with a KL-divergence budget so general capability is preserved.

Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.

From the publisher’s model card

“The very low KL divergence (0.094, far below the 0.5 “damage” threshold) means the model retains essentially all of its original capabilities and coherence.”

Running it

Commands are templates — confirm the exact repository and quant file before use.

Ollama (publisher-documented)
ollama run richardyoung/hemmingway-1-heretic
llama.cpp / GGUF
hf download Abiray/Hemmingway-1-heretic-GGUF --local-dir ./hemmingway-1-heretic
llama-cli -m ./hemmingway-1-heretic/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "richardyoung/Hemmingway-1-heretic"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve richardyoung/Hemmingway-1-heretic --trust-remote-code

Downloads and variants (14)

Every published repository of Hemmingway-1-heretic, including quantised re-releases by other authors.

Security-team assessment

Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.

  • Hemmingway-1-heretic will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
  • The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
  • Declared licence is cc-by-nc-4.0, but the terms that bind you are Altworld/Hemmingway-1’s — a re-release cannot grant more than its parent.

Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.

Metadata for Hemmingway-1-heretic is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with richardyoung, and does not independently verify publisher claims. See responsible use.