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

arzaan789/smollm-360m-uncensored

Name: arzaan789/smollm-360m-uncensored
Author: arzaan789

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/arzaan789%2Fsmollm-360m-uncensored"

Response includes

classification m8
files 13
hub_downloads_all_time 2,099
author_summary 28 models
readme_text full

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

Abliteration classifier · v1.0.0

Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.

Confidence

MEDIUM

Inherited from base model

M1 Direct removal →

Why this label 3 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.

'abliterated' in name/tags
is_gguf=1
assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown

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

490 last 30d - stable

Likes

Model age

5mo ago

created 2026-04-29

Downloads over time

Apr 29 → Oct 11 · 63 snapshots · spans 165 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

HuggingFaceTB/SmolLM-360M-Instruct this lineage

arzaan789/smollm-360m-uncensored↓ 490

Metadata

License

apache-2.0

Quantizations

F16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0

Files by quantization

F16 1 file 692 MB

smollm_360m_uncensored.f16.gguf

692 MB

9fe4f81b

download

Q8_0 1 file 369 MB

smollm_360m_uncensored.Q8_0.gguf

369 MB

5e75ca23

download

Q6_K 1 file 350 MB

smollm_360m_uncensored.Q6_K.gguf

350 MB

fa81eee0

download

Q5_K 2 files 547 MB

smollm_360m_uncensored.Q5_K_M.gguf	277 MB	de4acbde	download
smollm_360m_uncensored.Q5_K_S.gguf	270 MB	6d1fc42a	download

Q4_K 2 files 506 MB

smollm_360m_uncensored.Q4_K_M.gguf	258 MB	4c0d87a4	download
smollm_360m_uncensored.Q4_K_S.gguf	248 MB	e11a00d8	download

Q3_K 3 files 667 MB

smollm_360m_uncensored.Q3_K_L.gguf	235 MB	e4f40581	download
smollm_360m_uncensored.Q3_K_M.gguf	224 MB	8e2c40ca	download
smollm_360m_uncensored.Q3_K_S.gguf	209 MB	a30647d5	download

Q2_K 1 file 209 MB

smollm_360m_uncensored.Q2_K.gguf

209 MB

44a708d6

download

Auxiliary files 2 files 3.54 KB

.gitattributes	2.24 KB	bfbc4905	download
README.md	1.30 KB	225156eb	download

README current version from Hugging Face

license: apache-2.0
base_model: HuggingFaceTB/SmolLM-360M-Instruct
tags:

uncensored
abliterated
gguf
smollm
conversational
pipeline_tag: text-generation

smollm-360m-uncensored

Uncensored variant of HuggingFaceTB/SmolLM-360M-Instruct.

Method

Abliteration (strength=0.2) — refusal direction removed from all layers
LoRA fine-tune on Guilherme34/uncensor (2 epochs, r=16, alpha=32)
Re-abliteration (strength=0.35) — stronger pass to remove residual refusals

Eval Results

Split	Refused
Harmful (64 prompts)	0/64
Harmless (64 prompts)	16/64

Usage

llama-cli -m smollm_360m_uncensored.Q4_K_M.gguf -p "Your prompt here"

Training Config

Parameter	Value
Base Model	HuggingFaceTB/SmolLM-360M-Instruct
Fine-tune Dataset	Guilherme34/uncensor
Epochs	2
LoRA r	16
LoRA alpha	32
Learning Rate	0.0002
Abliteration Strength	0.2
Re-abliteration Strength	0.35

Credits

Abliteration technique: andyrdt/refusal_direction
Weight editing: Sumandora/remove-refusals-with-transformers

README history 1 version

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

2026-04-29Upload README.md with huggingface_hub35755091.3 KB
Loading...

arzaan789/smollm-360m-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

Repackaging (quantization)

Genealogy 0 direct forks

Metadata

Related

Files by quantization

README current version from Hugging Face

smollm-360m-uncensored

Method

Eval Results

Usage

Training Config

Credits

README history 1 version

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