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

libvm/mm-cand-v3-lot_paper_uncensored_refusal_like

libvm Qwen 8.2B
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/libvm%2Fmm-cand-v3-lot_paper_uncensored_refusal_like"
Response includes
  • classification m-uncensored
  • files 16
  • hub_downloads_all_time 35
  • author_summary 7 models
  • readme_text full
Try next
GET/models?author=libvm
All 7 models by libvm
 GET/models?family=qwen&method=m-uncensored
Sibling qwen models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
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
How we label → About M-U →
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.

What is a refusal direction? →
Downloads · lifetime
35
6 last 30d - stable
Likes
0
Model age
4mo ago
created 2026-05-26
Downloads over time
Now38→from13↑192%
1221314113 on Jun 1038 on Oct 1238 on Oct 10JunJulAugSepOct
Jun 10 → Oct 12 · 58 snapshots · spans 124 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.

Qwen/Qwen3-8B-Base this lineage
libvm/mm-cand-v3-lot_paper_uncensored_refusal_like↓ 6

Metadata

Tags
safetensors qwen3 model-merging lot-merging text-generation conversational arxiv:2505.23859 base_model:OpenDataArena/Qwen3-8B-ODA-Math-460k base_model:finetune:OpenDataArena/Qwen3-8B-ODA-Math-460k region:us

Related

Other by libvm
mm-cand-aim_on_task_arithmetic__calib_uncensored_refusal_like 11 mm-cand-aim_on_breadcrumbs__calib_uncensored_refusal_like 8 mm-cand-lot_paper_uncensored_refusal_like 8 mm-cand-aim_on_dare__calib_uncensored_refusal_like 7 mm-cand-aim_on_ties__calib_uncensored_refusal_like 6
Same base model
libvm/mm-cand-aim_on_task_arithmetic__calib_uncensored_refusal_like 11 libvm/mm-cand-aim_on_breadcrumbs__calib_uncensored_refusal_like 8 libvm/mm-cand-aim_on_dare__calib_uncensored_refusal_like 7 libvm/mm-cand-aim_on_ties__calib_uncensored_refusal_like 6 libvm/mm-cand-aim_on_della__calib_uncensored_refusal_like 6
Total size
15.3 GB
Files
16
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-05-26 19:27
Source huggingface.co/libvm/mm-cand-v3-lot_paper_uncensored_refusal_like ↗ Base model Qwen/Qwen3-8B-Base ↗

Files by quantization

Auxiliary files 16 files 15.3 GB
model-00001-of-00005.safetensors 3.72 GB 07fbb7c0 download
model-00002-of-00005.safetensors 3.72 GB 3d77b7ee download
model-00003-of-00005.safetensors 3.69 GB 3315dda7 download
model-00004-of-00005.safetensors 2.97 GB 39ca5443 download
model-00005-of-00005.safetensors 1.16 GB a24fa362 download
tokenizer.json 10.9 MB aeb13307 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
merge_manifest.json 191 KB 619f8f9b download
model.safetensors.index.json 32.1 KB 6b926301 download
tokenizer_config.json 9.50 KB 417d038a download
.gitattributes 1.53 KB 52373fe2 download
README.md 884 B bbd28066 download
config.json 729 B c5c5b1c6 download
upload_complete.json 490 B 571f6c25 download
generation_config.json 239 B 20a8a915 download

README current version from Hugging Face

base_model:

  • Qwen/Qwen3-8B-Base
  • Qwen/Qwen3-8B
  • OpenDataArena/Qwen3-8B-ODA-Math-460k
  • mlabonne/Qwen3-8B-abliterated
    pipeline_tag: text-generation
    tags:
  • model-merging
  • qwen3
  • lot-merging

This model was produced by merging Qwen/Qwen3-8B-Base with Qwen/Qwen3-8B, OpenDataArena/Qwen3-8B-ODA-Math-460k, mlabonne/Qwen3-8B-abliterated using canonical LOT Merging (Sun et al., NeurIPS 2025; arXiv:2505.23859). The Eq. 9 closed-form (Moore-Penrose pseudoinverse) was used for all linear projections in attention and MLP blocks; Eq. 12 (per-dimension feature-norm-weighted average) was used for input_layernorm and post_attention_layernorm RMSNorm scales; embeddings, lm_head and the final norm fall back to the mean of task vectors. Calibration source per specialist: instruction=uncensored_refusal_like, reasoning=uncensored_refusal_like, uncensored=uncensored_refusal_like.

README history 1 version

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

  1. 2026-05-26Add files using upload-large-folder tool6917c90884 B
    Loading...
Catalog is the map. Apps are the tools.

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

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration