← back to catalog · registered 2026-11-05 23:02

Guilherme34/TwIL-8B-Abliterated-Uncensored

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/Guilherme34%2FTwIL-8B-Abliterated-Uncensored"
Response includes
  • classification m1
  • files 18
  • author_summary 18 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
30
Likes
2
Descendants
3
in 3 direct forks
Model age
today
created 2026-11-05
Downloads over time
Now0→from0↑0%
00110 on Nov 50 on Nov 6Nov
Nov 5 → Nov 6 · 2 snapshots · spans 1 day

Genealogy 3 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.

Variants by this author 2 formats · 35 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Tags
safetensors granite base_model:webAI-Official/TwIL-8B base_model:finetune:webAI-Official/TwIL-8B region:us

Related

Total size
16.4 GB
Files
18
Quantizations
1
Registered
2026-11-05 23:02
Last updated on HF
2026-11-06 04:46

Files by quantization

Auxiliary files 18 files 16.4 GB
model-00004-of-00009.safetensors 1.86 GB f529473a download
model-00005-of-00009.safetensors 1.86 GB 949c0b7b download
model-00006-of-00009.safetensors 1.86 GB 4209653d download
model-00007-of-00009.safetensors 1.86 GB 41f7a72e download
model-00008-of-00009.safetensors 1.86 GB 9949b564 download
model-00003-of-00009.safetensors 1.86 GB d4a123b1 download
model-00002-of-00009.safetensors 1.86 GB 2e9f9016 download
model-00001-of-00009.safetensors 1.78 GB 3a8dacce download
model-00009-of-00009.safetensors 1.61 GB 4854b8e2 download
tokenizer.json 6.82 MB 49041102 download
model.safetensors.index.json 29.2 KB 9e69709b download
chat_template.jinja 8.80 KB e5c9466d download
abliteration_metadata.json 5.83 KB e1361b6c download
.gitattributes 1.48 KB a6344aac download
config.json 827 B e6dface0 download
tokenizer_config.json 400 B b193ab10 download
generation_config.json 207 B 4a4dffd7 download
README.md 44.0 B a4685b1f download

README current version from Hugging Face


base_model:

  • webAI-Official/TwIL-8B

README history 1 version

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

  1. 2026-11-05Create README.mdfa2004344 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.

Open in Abliteration