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

EDominguezISI/qwen25-7b-abliterated-finetuned-RedTeam

EDominguezISI Qwen 7.6B GGUF 33K ctx
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/EDominguezISI%2Fqwen25-7b-abliterated-finetuned-RedTeam"
Response includes
  • classification m8
  • files 8
  • hub_downloads_all_time 870
  • author_summary 2 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
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.

What is a refusal direction? →
Downloads · lifetime
870
196 last 30d - stable
Likes
0
Model age
7mo ago
created 2026-03-08
Downloads over time
Now909→from159↑472%
122409697984159 on Mar 11909 on Oct 11909 on Oct 10MarAprMayJunJulAugSepOct
Mar 11 → Oct 11 · 70 snapshots · spans 214 days

Metadata

Tags
safetensors gguf qwen2 endpoints_compatible region:us conversational

Related

Total size
21.7 GB
Files
8
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-03-08 21:40

Files by quantization

Auxiliary files 8 files 21.7 GB
model.safetensors 14.2 GB 3a450a7b download
qwen25-attacker-finetuned_q8_0.gguf 7.54 GB e9b0e0e9 download
tokenizer.json 10.9 MB 81457677 download
chat_template.jinja 2.45 KB bdf7919a download
.gitattributes 1.60 KB 5c1cb617 download
config.json 1.34 KB f6c7150b download
tokenizer_config.json 855 B b9235651 download
generation_config.json 242 B ba6a62d5 download

README

The author did not publish a README.

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