Hemmingway-1-heretic
Otherheretic
from Altworld/Hemmingway-1
↓ 8.8K♥ 2214 repos
Hemmingway-1-Heretic-MTP-V3-Final
Hemmingway-1-Heretic-MTP-V3-Final is a Heretic-ablated variant of Altworld/Hemmingway-1, published on Hugging Face by brainnxdomain. It is cc-by-nc-4.0 licence. It is distributed across 5 repositories in GGUF, Transformers and GGUF (imatrix) formats, totalling 20.5K downloads.
Specification
- Model name
- Hemmingway-1-Heretic-MTP-V3-Final
- Source repository
- brainnxdomain/Hemmingway-1-Heretic-MTP-V3-Final
- Base model
- Altworld/Hemmingway-1
- Publisher
- brainnxdomain
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- cc-by-nc-4.0
- Task
- Unspecified
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, Transformers, GGUF (imatrix)
- First indexed
- 24 Sept 2026
- Last updated
- 26 Sept 2026
Ablation technique
How Hemmingway-1-Heretic-MTP-V3-Final 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
“V3 is the third and final release of our decensored Hemmingway-1, and the first that stays decensored with thinking on. V2 (trial 208) removed refusals only with thinking off: at low reasoning effort it refused 60 of 100 harmful prompts, and 87 at medium. V3 (trial 124) was searched and selected on thinking-mode...”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download brainnxdomain/Hemmingway-1-Heretic-MTP-V3-Final-GGUF --local-dir ./hemmingway-1-heretic-mtp-v3-final
llama-cli -m ./hemmingway-1-heretic-mtp-v3-final/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "brainnxdomain/Hemmingway-1-Heretic-MTP-V3-Final"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve brainnxdomain/Hemmingway-1-Heretic-MTP-V3-Final --trust-remote-codeDownloads and variants (4)
Every published repository of Hemmingway-1-Heretic-MTP-V3-Final, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| brainnxdomain/Hemmingway-1-Heretic-MTP-V3-Final-GGUF | GGUF | 16.1K |
| mradermacher/Hemmingway-1-Heretic-MTP-V3-Final-i1-GGUF | GGUF (imatrix) | 3.5K |
| mradermacher/Hemmingway-1-Heretic-MTP-V3-Final-GGUF | GGUF | 591 |
| brainnxdomain/Hemmingway-1-Heretic-MTP-V3-Finalsource | Transformers | 396 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Hemmingway-1-Heretic-MTP-V3-Final 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-MTP-V3-Final is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with brainnxdomain, and does not independently verify publisher claims. See responsible use.