⌦abliteratedmodels.org

Dolphin-Mistral-24B-Venice-Edition-heretic

Dolphin-Mistral-24B-Venice-Edition-heretic is a Heretic-ablated variant of mistralai/Mistral-Small-24B-Instruct-2501, published on Hugging Face by Yingyaeliae. It is 24B parameters, 24GB VRAM class class and apache-2.0 licence. It is distributed across 5 repositories in Transformers, GGUF and GGUF (imatrix) formats, totalling 7.7K downloads.

Heretic24BMistral10B – 25B↓ 7,707♥ 5
View on Hugging Face ↗Base model ↗

Specification

Model name
Dolphin-Mistral-24B-Venice-Edition-heretic
Source repository
Yingyaeliae/Dolphin-Mistral-24B-Venice-Edition-heretic
Base model
mistralai/Mistral-Small-24B-Instruct-2501
Publisher
Yingyaeliae
Parameters
24B
Hardware class
10B – 25B — 24GB VRAM class
Licence
apache-2.0
Task
Text generation
Context window
Not documented
Ablation scope
Not stated by the publisher
Formats available
Transformers, GGUF, GGUF (imatrix)
First indexed
21 Nov 2025
Last updated
6 Aug 2026

Ablation technique

How Dolphin-Mistral-24B-Venice-Edition-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

“This model was trained on 8xB200 provided by https://targon.com/”

Running it

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

llama.cpp / GGUF
hf download mradermacher/Dolphin-Mistral-24B-Venice-Edition-heretic-i1-GGUF --local-dir ./dolphin-mistral-24b-venice-edition-heretic
llama-cli -m ./dolphin-mistral-24b-venice-edition-heretic/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "Yingyaeliae/Dolphin-Mistral-24B-Venice-Edition-heretic"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve Yingyaeliae/Dolphin-Mistral-24B-Venice-Edition-heretic --trust-remote-code

Downloads and variants (4)

Every published repository of Dolphin-Mistral-24B-Venice-Edition-heretic, including quantised re-releases by other authors.

RepositoryFormatDownloads
mradermacher/Dolphin-Mistral-24B-Venice-Edition-heretic-i1-GGUFGGUF (imatrix)4.6K
mradermacher/Dolphin-Mistral-24B-Venice-Edition-heretic-GGUFGGUF2.9K
Yingyaeliae/Dolphin-Mistral-24B-Venice-Edition-hereticsourceTransformers204
askalgore/Dolphin-Mistral-24B-Venice-Edition-hereticTransformers6

Security-team assessment

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

  • Dolphin-Mistral-24B-Venice-Edition-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.
  • Capability is inherited from mistralai/Mistral-Small-24B-Instruct-2501, not added by ablation — at 24B parameters, expect roughly the base model’s competence, minus some instruction-following fidelity.
  • The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
  • Declared licence is apache-2.0, but the terms that bind you are mistralai/Mistral-Small-24B-Instruct-2501’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 Dolphin-Mistral-24B-Venice-Edition-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 Yingyaeliae, and does not independently verify publisher claims. See responsible use.