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

ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated

ussoewwin Qwen 7B multimodal
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/ussoewwin%2FQwen2.5-VL-7B-Instruct-abliterated"
Response includes
  • classification m1
  • files 3
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=ussoewwin
All 3 models by ussoewwin
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
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)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · 30-day
0
Likes
3
Model age
9mo ago
created 2026-01-12
Downloads over time
Now0→from0↑0%
00110 on Jan 140 on Oct 11JanMarMayJulSep
Jan 14 → Oct 11 · 78 snapshots · spans 270 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/Qwen2.5-VL-7B-Instruct this lineage
ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated

Metadata

License
apache-2.0
Languages
en
Tags
transformers vision image-to-text text-generation multimodal abliterated fp16 en base_model:Qwen/Qwen2.5-VL-7B-Instruct base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct license:apache-2.0 endpoints_compatible

Related

Other by ussoewwin
qwen3_4b_8b_abliterated_fp16 0 qwen3_4b_8b_abliterated_fp16_convrot_int8 0
Same base model
huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated 301K Andycurrent/Qwen2.5-VL-7B-Abliterated-Caption-it_GGUF 455 falacal/Qwen2.5-VL-7B-fp8-Abliterated-Caption-it 103 prithivMLmods/Qwen2.5-VL-7B-Abliterated-Caption-it 66 shagg69/Qwen2.5-VL-7B-Abliterated-Caption-it 18
Total size
15.4 GB
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-01-12 02:37
Source huggingface.co/ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated ↗ Base model Qwen/Qwen2.5-VL-7B-Instruct ↗

Files by quantization

Auxiliary files 3 files 15.4 GB
Qwen2.5-VL-7B-Instruct-abliterated_converted.safetensors 15.4 GB d6368f80 download
.gitattributes 1.48 KB a6344aac download
README.md 973 B 158da0a1 download

README current version from Hugging Face

base_model: Qwen/Qwen2.5-VL-7B-Instruct
language:

  • en
    license: apache-2.0
    library_name: transformers
    tags:
  • vision
  • image-to-text
  • text-generation
  • multimodal
  • abliterated
  • fp16

Qwen2.5-VL-7B-Instruct-abliterated (Merged FP16)

This repository contains the merged FP16 weights of the abliterated version of Qwen2.5-VL-7B-Instruct.

I have simply merged the split files originally provided by ussoewwin into a unified model for easier handling and deployment.

Model Details

README history 3 versions

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

  1. 2026-01-12Update README.md8bbfad7973 B
    Loading...
  2. 2026-01-12Update README.md0117b501.2 KB
    Loading...
  3. 2026-01-12initial commit4e2ed8028 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