supergemma4-26b-uncensored-v2
26BOtheruncensored
from google/gemma-4-26B-A4B-it
↓ 394K♥ 98442 repos
WizardLM-Uncensored-SuperCOT-StoryTelling-30b
WizardLM-Uncensored-SuperCOT-StoryTelling-30b is a abliterated and uncensored variant of Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b, published on Hugging Face by Monero. It is 30B parameters and 48GB VRAM class class. It is distributed across 6 repositories in Transformers, GPTQ, AWQ and GGUF formats, totalling 6.5K downloads.
Specification
- Model name
- WizardLM-Uncensored-SuperCOT-StoryTelling-30b
- Source repository
- Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b
- Publisher
- Monero
- Parameters
- 30B
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- Not declared
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GPTQ, AWQ, GGUF
- First indexed
- 31 May 2023
- Last updated
- 9 Nov 2023
Ablation technique
How WizardLM-Uncensored-SuperCOT-StoryTelling-30b 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 model is a triple model merge of WizardLM Uncensored+CoT+Storytelling, resulting in a comprehensive boost in reasoning and story writing capabilities.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-GGUF --local-dir ./wizardlm-uncensored-supercot-storytelling-30b
llama-cli -m ./wizardlm-uncensored-supercot-storytelling-30b/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b --trust-remote-codeDownloads and variants (5)
Every published repository of WizardLM-Uncensored-SuperCOT-StoryTelling-30b, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-GGUF | GGUF | 6.3K |
| Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30bsource | Transformers | 166 |
| TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-GPTQ | GPTQ | 81 |
| TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-AWQ | AWQ | 13 |
| TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-GGML | Transformers | 0 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- WizardLM-Uncensored-SuperCOT-StoryTelling-30b 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 Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b, not added by ablation — at 30B 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.
- 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.
- No licence is declared on this repository, which is a compliance problem in itself. Resolve it against the base model’s terms before use.
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-Uncensored-SuperCOT-StoryTelling-30b is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with Monero, and does not independently verify publisher claims. See responsible use.