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

TroyDoesAI/Abliterated-Merge-WIP-2

TroyDoesAI Llama 8.0B
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/TroyDoesAI%2FAbliterated-Merge-WIP-2"
Response includes
  • classification m1
  • files 11
  • hub_downloads_all_time 52
  • author_summary 8 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 · lifetime
52
16 last 30d - stable
Likes
0
Model age
2.2y ago
created 2024-07-14
Downloads over time
Now56→from0↑0%
02347700 on Oct 23, 202456 on Oct 1164 on Sep 10, 2025Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 23, 2024 → Oct 11 · 142 snapshots · spans 718 days

Metadata

License
apache-2.0
Tags
transformers safetensors llama text-generation conversational license:apache-2.0 text-generation-inference endpoints_compatible region:us

Related

Total size
15.0 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-07-14 16:40

Files by quantization

Auxiliary files 11 files 15.0 GB
model-00002-of-00004.safetensors 4.66 GB 98e4ca60 download
model-00001-of-00004.safetensors 4.61 GB 8f816be5 download
model-00003-of-00004.safetensors 4.58 GB bc0144e5 download
model-00004-of-00004.safetensors 1.11 GB 9e4e4ca5 download
tokenizer.json 8.66 MB 84a48d32 download
tokenizer_config.json 56.7 KB ee089839 download
model.safetensors.index.json 22.3 KB c45189ef download
.gitattributes 1.48 KB a6344aac download
config.json 737 B f9858e04 download
special_tokens_map.json 467 B 6a9ba8de download
README.md 31.0 B 7b95401d download

README current version from Hugging Face


license: apache-2.0

README history 1 version

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

  1. 2024-07-14initial commitb805aaa28 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