Spark-x2.5-4B-Heretic-jp
4BOtherheretic
from XHToken/Spark-X2.5-4B
↓ 452.1K♥ 182 repos
WizardLM-7B-Uncensored
WizardLM-7B-Uncensored is a abliterated and uncensored variant of QuixiAI/WizardLM-7B-Uncensored, published on Hugging Face by QuixiAI. It is 7B parameters, single consumer GPU class and other licence. It is distributed across 36 repositories in Transformers, GGUF, GPTQ and AWQ formats, totalling 20.5K downloads.
Specification
- Model name
- WizardLM-7B-Uncensored
- Source repository
- QuixiAI/WizardLM-7B-Uncensored
- Base model
- QuixiAI/WizardLM-7B-Uncensored
- Publisher
- QuixiAI
- Parameters
- 7B
- VRAM required
- ~5 GB at Q4_K_M, 4k context (estimated) — runs on 6 GB cards
- Hardware class
- 4B – 10B — single consumer GPU
- Licence
- other
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GPTQ, AWQ, GGUF (imatrix)
- First indexed
- 4 May 2023
- Last updated
- 20 Oct 2026
Ablation technique
How WizardLM-7B-Uncensored was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
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 is WizardLM trained with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download TheBloke/WizardLM-7B-uncensored-GGUF --local-dir ./wizardlm-7b-uncensored
llama-cli -m ./wizardlm-7b-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "QuixiAI/WizardLM-7B-Uncensored"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve QuixiAI/WizardLM-7B-Uncensored --trust-remote-codeDownloads and variants (35)
Every published repository of WizardLM-7B-Uncensored, 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.
- WizardLM-7B-Uncensored 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 QuixiAI/WizardLM-7B-Uncensored, not added by ablation — at 7B parameters, expect a small model’s reasoning and a high error rate on exploit detail.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
- Declared licence is other, but the terms that bind you are QuixiAI/WizardLM-7B-Uncensored’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 WizardLM-7B-Uncensored is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with QuixiAI, and does not independently verify publisher claims. See responsible use.