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

RichardErkhov/BlossomsAI_-_vmlu-llm-7B-Uncensored-gguf

Name: RichardErkhov/BlossomsAI_-_vmlu-llm-7B-Uncensored-gguf
Author: RichardErkhov

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/RichardErkhov%2FBlossomsAI_-_vmlu-llm-7B-Uncensored-gguf"

Response includes

classification m8
files 24
hub_downloads_all_time 5,397
author_summary 257 models
readme_text full

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

Abliteration classifier · v1.0.0

Primary method

Repackaging (quantization)

No other method signals detected in this model.

Confidence

MEDIUM

Why this label 2 signals

Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.

author=richarderkhov (M8 quantization producer)
is_gguf=1

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

619 last 30d - stable

Likes

Model age

17mo ago

created 2025-04-21

Downloads over time

Apr 16, 2025 → Oct 11 · 117 snapshots · spans 543 days

Metadata

Quantizations

IQ3 IQ4 Q2_K Q3_K Q4 Q4_K Q5 Q5_K Q6_K Q8_0

Files by quantization

Q8_0 1 file 7.22 GB

vmlu-llm-7B-Uncensored.Q8_0.gguf

7.22 GB

0068947b

download

Q6_K 1 file 5.57 GB

vmlu-llm-7B-Uncensored.Q6_K.gguf

5.57 GB

dd335345

download

Q5 2 files 9.80 GB

vmlu-llm-7B-Uncensored.Q5_1.gguf	5.11 GB	2fe47602	download
vmlu-llm-7B-Uncensored.Q5_0.gguf	4.69 GB	27df879e	download

Q5_K 3 files 14.3 GB

vmlu-llm-7B-Uncensored.Q5_K.gguf	4.82 GB	dec4aac2	download
vmlu-llm-7B-Uncensored.Q5_K_M.gguf	4.82 GB	dec4aac2	download
vmlu-llm-7B-Uncensored.Q5_K_S.gguf	4.69 GB	22d86206	download

Q4 2 files 8.14 GB

vmlu-llm-7B-Uncensored.Q4_1.gguf	4.28 GB	016c5b58	download
vmlu-llm-7B-Uncensored.Q4_0.gguf	3.86 GB	feffabfc	download

Q4_K 3 files 12.1 GB

vmlu-llm-7B-Uncensored.Q4_K.gguf	4.10 GB	dc1205a6	download
vmlu-llm-7B-Uncensored.Q4_K_M.gguf	4.10 GB	dc1205a6	download
vmlu-llm-7B-Uncensored.Q4_K_S.gguf	3.89 GB	104a5279	download

IQ4 2 files 7.61 GB

vmlu-llm-7B-Uncensored.IQ4_NL.gguf	3.90 GB	92c544bf	download
vmlu-llm-7B-Uncensored.IQ4_XS.gguf	3.71 GB	3dba2e02	download

Q3_K 4 files 13.2 GB

vmlu-llm-7B-Uncensored.Q3_K_L.gguf	3.59 GB	8ba8a85c	download
vmlu-llm-7B-Uncensored.Q3_K.gguf	3.31 GB	51ab04c7	download
vmlu-llm-7B-Uncensored.Q3_K_M.gguf	3.31 GB	51ab04c7	download
vmlu-llm-7B-Uncensored.Q3_K_S.gguf	2.98 GB	a5a43c1b	download

IQ3 3 files 8.93 GB

vmlu-llm-7B-Uncensored.IQ3_M.gguf	3.09 GB	ae44b698	download
vmlu-llm-7B-Uncensored.IQ3_S.gguf	2.99 GB	aaf00d10	download
vmlu-llm-7B-Uncensored.IQ3_XS.gguf	2.84 GB	a9494170	download

Q2_K 1 file 2.56 GB

vmlu-llm-7B-Uncensored.Q2_K.gguf

2.56 GB

e4b830f3

download

Auxiliary files 2 files 8.51 KB

README.md	5.52 KB	7e7b888e	download
.gitattributes	2.99 KB	431b968f	download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

vmlu-llm-7B-Uncensored - GGUF

Model creator: https://huggingface.co/BlossomsAI/
Original model: https://huggingface.co/BlossomsAI/vmlu-llm-7B-Uncensored/

Name	Quant method	Size
vmlu-llm-7B-Uncensored.Q2_K.gguf	Q2_K	2.56GB
vmlu-llm-7B-Uncensored.IQ3_XS.gguf	IQ3_XS	2.84GB
vmlu-llm-7B-Uncensored.IQ3_S.gguf	IQ3_S	2.99GB
vmlu-llm-7B-Uncensored.Q3_K_S.gguf	Q3_K_S	2.98GB
vmlu-llm-7B-Uncensored.IQ3_M.gguf	IQ3_M	3.09GB
vmlu-llm-7B-Uncensored.Q3_K.gguf	Q3_K	3.31GB
vmlu-llm-7B-Uncensored.Q3_K_M.gguf	Q3_K_M	3.31GB
vmlu-llm-7B-Uncensored.Q3_K_L.gguf	Q3_K_L	3.59GB
vmlu-llm-7B-Uncensored.IQ4_XS.gguf	IQ4_XS	3.71GB
vmlu-llm-7B-Uncensored.Q4_0.gguf	Q4_0	3.86GB
vmlu-llm-7B-Uncensored.IQ4_NL.gguf	IQ4_NL	3.9GB
vmlu-llm-7B-Uncensored.Q4_K_S.gguf	Q4_K_S	3.89GB
vmlu-llm-7B-Uncensored.Q4_K.gguf	Q4_K	4.1GB
vmlu-llm-7B-Uncensored.Q4_K_M.gguf	Q4_K_M	4.1GB
vmlu-llm-7B-Uncensored.Q4_1.gguf	Q4_1	4.28GB
vmlu-llm-7B-Uncensored.Q5_0.gguf	Q5_0	4.69GB
vmlu-llm-7B-Uncensored.Q5_K_S.gguf	Q5_K_S	4.69GB
vmlu-llm-7B-Uncensored.Q5_K.gguf	Q5_K	4.82GB
vmlu-llm-7B-Uncensored.Q5_K_M.gguf	Q5_K_M	4.82GB
vmlu-llm-7B-Uncensored.Q5_1.gguf	Q5_1	5.11GB
vmlu-llm-7B-Uncensored.Q6_K.gguf	Q6_K	5.57GB
vmlu-llm-7B-Uncensored.Q8_0.gguf	Q8_0	7.22GB

Original model description:

library_name: transformers
license: mit
language:

en
vi
base_model:
vtrungnhan9/vmlu-llm

🎯 vmlu-llm-7B-Uncensored

An optimized version of vmlu-llm focused on removing refusal behaviors

📌 Overview

A streamlined implementation that removes refusal behaviors from vtrungnhan9/vmlu-llm, based on directional intervention techniques.

🔍 Key Features

Implements directional intervention for behavior modification
Fully quantized for resource-efficient deployment

🛠️ Implementation

Based on research findings from "Refusal in LLMs is Mediated by a Single Direction"

💫 Quantization

Pre-quantized models available in GGFU format:

🤝 Contributors

Developed with ❤️ by BlossomAI

_{Star ⭐️ this repo if you find it valuable!}

README history 1 version

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

2025-04-21uploaded readme2bc6c005.5 KB
Loading...

RichardErkhov/BlossomsAI_-_vmlu-llm-7B-Uncensored-gguf

The browser can't see your hardware

The Abliteration app is integrated with your machine

And you can chat with any model, right now

Repackaging (quantization)

Metadata

Related

Files by quantization

README current version from Hugging Face

Original model description:

🎯 vmlu-llm-7B-Uncensored

An optimized version of vmlu-llm focused on removing refusal behaviors

📌 Overview

🔍 Key Features

🛠️ Implementation

💫 Quantization

🤝 Contributors

README history 1 version

Run models on your own machine, not in the cloud.