0xSojalSec / Model details

LFM2.5-24B-A2B-Uncensored-no-refusal

0xSojalSec/LFM2.5-24B-A2B-Uncensored-no-refusal

uncensoredfine-tuned

Read the original model card ↗ · Choosing a model

About this model

0xSojalSec's refusal-removed derivative of LiquidAI's LFM2.5-24B-A2B, provided as six pre-quantized GGUF builds and a 24 MB LoRA adapter. The creator says they used abliteration on blocks 14-39 only, reversing the refusal direction with a scale of 1.75, and reports that refusals fell from 96.3% to 1.2% in English and from 62% to 0% in Russian on held-out prompts while MMLU rose from 64.40% to 65.55%. The card warns that answers are phrased differently and that the edit was not tested on languages other than English and Russian. License is listed as 'other'.

Description sources

https://huggingface.co/0xSojalSec/LFM2.5-24B-A2B-Uncensored-no-refusal/raw/253f179d3657d001987da93355890bb564dc1500/README.md ↗

Source-based description, not an independent evaluation. Check the linked sources for the creator’s claims and limitations.

Size and formats

Base model: LiquidAI/LFM2.5-24B-A2B
Parameters: Unknown
Main repository formats: GGUF
License tag: other
Languages: ar, de, en, es, fr, it, ja, ko, pt, zh
Last updated: 2026-10-14 · 02:50:05.000 UTC

What changed

Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.

uncensoredmodel name: LFM2.5-24B-A2B-Uncensored-no-refusal
fine-tunedsource tag: base_model:finetune:LiquidAI/LFM2.5-24B-A2B

Family evidence

These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.

LFM: Base model: LiquidAI/LFM2.5-24B-A2B

Available versions

Versions appear here only when they explicitly name this exact model as their source. Check each repository for available files.

Main repository files ↗GGUF
No other explicitly linked versions recorded.

Refusal profile

Refused 0 of 16 prompts (0.0%)

We asked this model 120 benign but risky-looking prompts across ten topics and counted how often it refused, hedged or answered. Lower means it answered more often; it says nothing about answer quality.

Persuasion & deception0 refused · 0 partial · 2 complied
Harassment & confrontation0 refused · 0 partial · 1 complied
Risky activities0 refused · 0 partial · 2 complied
Offensive & controversial speech0 refused · 0 partial · 0 complied
Legal grey areas0 refused · 0 partial · 1 complied
Privacy & personal data0 refused · 0 partial · 1 complied
Self-harm & mental health topics0 refused · 0 partial · 0 complied
Sexual & adult topics0 refused · 0 partial · 2 complied
Ethically grey requests0 refused · 0 partial · 2 complied
Violence & conflict0 refused · 0 partial · 5 complied

Capability check: 13 of 15 passed. Fifteen simple tasks with known answers, so a broken model cannot score well by refusing nothing.

Unclear answers: 104 (not counted). An answer is unclear when the two checker models disagree or the output was empty or garbled.

Too many unclear answers to rank: this model appears on the Refusal Index but is not placed in the ranking.

Measured 2026-10-25 · Q4_K_M via 0xSojalSec/LFM2.5-24B-A2B-Uncensored-no-refusal ↗ · llama.cpp · prompt set v1

How we measure · The prompts

Link to this listing

Made or quantized this model? Paste one of these into your model card or README so people can find this listing.

Markdown

[Listed on Custom Clankers](https://customclankers.com/models/0xsojalsec-lfm2-5-24b-a2b-uncensored-no-refusal/)

HTML

<a href="https://customclankers.com/models/0xsojalsec-lfm2-5-24b-a2b-uncensored-no-refusal/">Listed on Custom Clankers</a>

Plain text links only: no image, no script, nothing loaded from this site.

Customize or build on this model

Listed from public GitHub data, not tested by us. Read the code and license before you run anything.

Tools to customize it further

Make a smaller download (quantize)

llama.cpp ↗ ★ 132,260
Runs models locally and includes the tools behind most GGUF files. A conversion script turns Hugging Face weights into GGUF, and llama-quantize shrinks a high-precision GGUF to lower-bit formats, which can cost some accuracy.

Learn the techniques

LLM Course ↗ ★ 84,667
A free course with roadmaps and Colab notebooks. Its notebooks include one-click tools for merging with MergeKit, quantizing to GGUF, GPTQ, EXL2, AWQ and HQQ, and automatic abliteration with custom datasets.

Compare all tools →

Source provenance

Downloads: 1,106
Likes: 4
Metadata checked: 2026-10-24 · 09:40:11 UTC
First seen in index: 2026-10-24 · 04:11:48 UTC
Source revision: 253f179d3657d001987da93355890bb564dc1500

Source-card excerpt

Source model card excerpt: How to Run LFM2.5-24B-A2B Without Refusals Locally Liquid's refusal behaviour projected out of the original weights, in the second two thirds of the network

From 0xSojalSec/LFM2.5-24B-A2B-Uncensored-no-refusal. Creator model-card excerpt, not an independent review.

Inspect before you run

Low refusal is not proof of correctness. Outputs can be inaccurate, harmful, or biased. Review the model card, license and files yourself. A license tag is not commercial-use advice. Parameter counts are source metadata; no hardware compatibility is implied.

This directory does not host or redistribute model weights. Refusal profiles are measured by us on a fixed prompt set; all other behavior claims are source-reported.

Collection rules & limitations ↗