← back to catalog · registered 2026-08-22 13:56

concedo/Vicuzard-30B-Uncensored

Name: concedo/Vicuzard-30B-Uncensored
Author: concedo

Your rig guess connected

? Why do I need an app?

Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/concedo%2FVicuzard-30B-Uncensored"

Response includes

classification m-uncensored
files 20
hub_downloads_all_time 55,817
author_summary 2 models
readme_text full

10 credits · hourly refresh · ~4 KB payload Get an API key →

Abliteration classifier · v1.0.0

M-U

Primary method

Uncensored (method unknown)

No other method signals detected in this model.

Confidence

LOW

Why this label 3 signals

Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.

'uncensored' in name/tags but no 'abliterated' marker
method not identifiable from author declaration alone
may be DPO fine-tune, prompt engineering, or unknown technique

Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

Downloads · lifetime

56K

199 last 30d - cooling

Likes

Model age

3.3y ago

created 2023-06-09

Downloads over time

Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Metadata

License

other

Languages

Files by quantization

Auxiliary files 20 files 60.6 GB

pytorch_model-00003-of-00011.bin	5.81 GB	f676b9ae	download
pytorch_model-00008-of-00011.bin	5.81 GB	fb25aef4	download
pytorch_model-00007-of-00011.bin	5.81 GB	a1c8f441	download
pytorch_model-00002-of-00011.bin	5.81 GB	e7f0a5f0	download
pytorch_model-00006-of-00011.bin	5.76 GB	529032b0	download
pytorch_model-00005-of-00011.bin	5.76 GB	f16a33cb	download
pytorch_model-00010-of-00011.bin	5.76 GB	5fc40dde	download
pytorch_model-00004-of-00011.bin	5.76 GB	7f0f7d21	download
pytorch_model-00009-of-00011.bin	5.76 GB	5b2140da	download
pytorch_model-00001-of-00011.bin	5.71 GB	1ae78039	download
pytorch_model-00011-of-00011.bin	2.83 GB	1c8c14eb	download
tokenizer.json	1.76 MB	f57412e8	download
tokenizer.model	488 KB	9e556afd	download
pytorch_model.bin.index.json	48.9 KB	dfe91ae1	download
.gitattributes	1.44 KB	c7d9f333	download
README.md	910 B	9976f180	download
tokenizer_config.json	727 B	5ab645d5	download
config.json	581 B	8542e338	download
generation_config.json	132 B	66f8de0f	download
added_tokens.json	21.0 B	e41416dd	download

README current version from Hugging Face

license: other
language:

Vicuzard-30B-Uncensored

This is an experimental mixed model containing a parameter-wise 50/50 blend (weighted average) of ehartford/Wizard-Vicuna-30B-Uncensored and ehartford/WizardLM-30B-Uncensored

GGML models are provided here, for use in KoboldCPP.

This improves on earlier model mixing techniques by only applying the merge to the layers containing tensors of the same dimensions.
By selectively skipping merge operations on the input and output layers, we are now able to merge models with different vocab sizes (i.e. added tokens) so long as the hidden layers have identical sizes.

All feedback and comments can be directed to Concedo on the KoboldAI discord.

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

2023-06-10Create README.mde2329c0910 B
Loading...

Discussions 4 threads

2025-05-01PRAdding `safetensors` variant of this modelopen1 💬#4
Loading...
2023-11-17PRAdding Evaluation Resultsopen1 💬#3
Loading...
2023-06-15cool idea! did it work?open2 💬#2
Loading...
2023-06-09PRUpload folder using huggingface_hubmerged3 💬#1
Loading...

Continue on Hugging Face →

concedo/Vicuzard-30B-Uncensored

The browser can't see your hardware

The Abliteration app is integrated with your machine

And you can chat with any model, right now