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

otherhalf-dev/Qwen2-VL-72B-Instruct-abliterated-FP8

otherhalf-dev Qwen 70B
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/otherhalf-dev%2FQwen2-VL-72B-Instruct-abliterated-FP8"
Response includes
  • classification m1
  • files 30
  • hub_downloads_all_time 199
  • author_summary 9 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
199
20 last 30d - stable
Likes
0
Model age
21mo ago
created 2025-01-03
Downloads over time
Now211→from2↑10,450%
0771552322 on Jan 22, 2025211 on Oct 12211 on Oct 10Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 22, 2025 → Oct 12 · 130 snapshots · spans 628 days

Metadata

License
apache-2.0
Tags
safetensors qwen2_vl license:apache-2.0 compressed-tensors region:us

Related

Total size
71.4 GB
Files
30
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-01-03 13:01

Files by quantization

Auxiliary files 30 files 71.4 GB
model-00001-of-00016.safetensors 4.58 GB 5670314d download
model-00004-of-00016.safetensors 4.54 GB df021f9e download
model-00006-of-00016.safetensors 4.54 GB 515b2f21 download
model-00008-of-00016.safetensors 4.54 GB 5100f1f9 download
model-00010-of-00016.safetensors 4.54 GB 4423d26c download
model-00012-of-00016.safetensors 4.54 GB 489079d0 download
model-00014-of-00016.safetensors 4.54 GB 0d383cc5 download
model-00002-of-00016.safetensors 4.54 GB e7389ebd download
model-00005-of-00016.safetensors 4.45 GB 4fdfa0a3 download
model-00007-of-00016.safetensors 4.45 GB e8903b0a download
model-00009-of-00016.safetensors 4.45 GB 2301eff8 download
model-00011-of-00016.safetensors 4.45 GB 7b2d2180 download
model-00013-of-00016.safetensors 4.45 GB ff3e1d1e download
model-00015-of-00016.safetensors 4.45 GB d17e077f download
model-00003-of-00016.safetensors 4.45 GB 4803ee6b download
model-00016-of-00016.safetensors 3.81 GB 4729ea9f download
tokenizer.json 10.9 MB 091aa759 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 153 KB fd8aeae9 download
config.json 6.56 KB b6f1ddac download
tokenizer_config.json 4.23 KB 84c1ef8e download
.gitattributes 1.53 KB 52373fe2 download
chat_template.json 1.02 KB 13303be6 download
special_tokens_map.json 613 B ac23c0aa download
preprocessor_config.json 567 B 2ef5e95d download
added_tokens.json 392 B caa81304 download
generation_config.json 222 B ec6d90f7 download
recipe.yaml 158 B 612675f4 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. 2025-01-03initial commite9cc72d28 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