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

arzaan789/smollm-135m-uncensored

Name: arzaan789/smollm-135m-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-135m-uncensored"

Response includes

classification m8
files 13
hub_downloads_all_time 1,728
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

412 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-135M-Instruct this lineage

arzaan789/smollm-135m-uncensored↓ 412

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 258 MB

smollm_135m_uncensored.f16.gguf

258 MB

dc126f20

download

Q8_0 1 file 138 MB

smollm_135m_uncensored.Q8_0.gguf

138 MB

d59e2b67

download

Q6_K 1 file 132 MB

smollm_135m_uncensored.Q6_K.gguf

132 MB

a9d88063

download

Q5_K 2 files 212 MB

smollm_135m_uncensored.Q5_K_M.gguf	107 MB	a6269aed	download
smollm_135m_uncensored.Q5_K_S.gguf	105 MB	05392c86	download

Q4_K 2 files 198 MB

smollm_135m_uncensored.Q4_K_M.gguf	101 MB	482cc257	download
smollm_135m_uncensored.Q4_K_S.gguf	97.3 MB	d019654b	download

Q3_K 3 files 266 MB

smollm_135m_uncensored.Q3_K_L.gguf	93.0 MB	3183ef07	download
smollm_135m_uncensored.Q3_K_M.gguf	89.2 MB	4e577fb2	download
smollm_135m_uncensored.Q3_K_S.gguf	84.1 MB	f2b72059	download

Q2_K 1 file 84.1 MB

smollm_135m_uncensored.Q2_K.gguf

84.1 MB

c16fd9c4

download

Auxiliary files 2 files 3.54 KB

.gitattributes	2.24 KB	237ad214	download
README.md	1.30 KB	100b768f	download

README current version from Hugging Face

license: apache-2.0
base_model: HuggingFaceTB/SmolLM-135M-Instruct
tags:

uncensored
abliterated
gguf
smollm
conversational
pipeline_tag: text-generation

smollm-135m-uncensored

Uncensored variant of HuggingFaceTB/SmolLM-135M-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_135m_uncensored.Q4_K_M.gguf -p "Your prompt here"

Training Config

Parameter	Value
Base Model	HuggingFaceTB/SmolLM-135M-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_hub54e14c81.3 KB
Loading...

arzaan789/smollm-135m-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-135m-uncensored

Method

Eval Results

Usage

Training Config

Credits

README history 1 version

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