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

createveai/Qwen2-VL-7B-Instruct-abliterated-4bit

createveai Qwen 7.4B multimodal second-order
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/createveai%2FQwen2-VL-7B-Instruct-abliterated-4bit"
Response includes
  • classification m1
  • files 15
  • hub_downloads_all_time 5,725
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=createveai
All 3 models by createveai
 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 · lifetime
6K
20 last 30d - cooling
Likes
0
Model age
22mo ago
created 2024-11-25
Downloads over time
Now5.7K→from0↑0%
02.1K4.2K6.3K0 on Nov 20, 20245.7K on Oct 115.7K on Oct 9Nov '24Feb '25May '25Aug '25Nov '25FebMayAug
Nov 20, 2024 → Oct 11 · 138 snapshots · spans 690 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.

huihui-ai/Qwen2-VL-7B-Instruct-abliterated this lineage
createveai/Qwen2-VL-7B-Instruct-abliterated-4bit↓ 20

Metadata

License
apache-2.0
Languages
en
Tags
transformers safetensors qwen2_vl image-text-to-text text-generation-inference unsloth trl conversational en base_model:huihui-ai/Qwen2-VL-7B-Instruct-abliterated base_model:quantized:huihui-ai/Qwen2-VL-7B-Instruct-abliterated license:apache-2.0

Related

Other by createveai
Llama-3.2-11B-Vision-Instruct-abliterated-4bit 45 Qwen2-VL-2B-Instruct-abliterated-4bit 26
Same base model
bartowski/Qwen2-VL-7B-Instruct-abliterated-GGUF 3K mradermacher/Qwen2-VL-7B-Instruct-abliterated-i1-GGUF 1K mradermacher/Qwen2-VL-7B-Instruct-abliterated-GGUF 832
Total size
5.49 GB
Files
15
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-11-25 10:35
Source huggingface.co/createveai/Qwen2-VL-7B-Instruct-abliterated-4bit ↗ Base model huihui-ai/Qwen2-VL-7B-Instruct-abliterated ↗

Files by quantization

Auxiliary files 15 files 5.51 GB
model-00001-of-00002.safetensors 4.48 GB b3650634 download
model-00002-of-00002.safetensors 1.02 GB e76ec4dc 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 205 KB 238b907f download
tokenizer_config.json 4.30 KB 1047c1fc download
config.json 1.55 KB 5f785588 download
.gitattributes 1.53 KB 52373fe2 download
chat_template.json 1.02 KB 13303be6 download
README.md 613 B 677c6b4a download
preprocessor_config.json 567 B 2ef5e95d download
special_tokens_map.json 500 B b0ba7ffb download
added_tokens.json 392 B caa81304 download
generation_config.json 272 B 9ae49139 download

README current version from Hugging Face

base_model: huihui-ai/Qwen2-VL-7B-Instruct-abliterated
tags:

  • text-generation-inference
  • transformers
  • unsloth
  • qwen2_vl
  • trl
    license: apache-2.0
    language:
  • en

Uploaded model

  • Developed by: createveai
  • License: apache-2.0
  • Finetuned from model : huihui-ai/Qwen2-VL-7B-Instruct-abliterated

This qwen2_vl model was trained 2x faster with Unsloth and Huggingface's TRL library.

README history 1 version

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

  1. 2024-11-25Upload README.md with huggingface_hub435a815613 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