Get the app
← back to catalog · registered 2026-10-29 09:01

SonGT1/Qwen2.5-1.5B-Instruct-abliterated

SonGT1 Qwen 1.5B GGUF
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/SonGT1%2FQwen2.5-1.5B-Instruct-abliterated"
Response includes
  • classification m8
  • files 9
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=qwen&method=m8
Sibling qwen models · same method
 GET/methods/m8
What "m8" means · taxonomy
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
M1 Direct removal →
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
How we label → About M8 →
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 · 30-day
0
Likes
1
Model age
today
created 2026-10-29

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/Qwen2.5-1.5B-Instruct this lineage
SonGT1/Qwen2.5-1.5B-Instruct-abliterated

Metadata

License
apache-2.0
Languages
zh en
Tags
safetensors gguf qwen2 qwen2.5 chinese English abliterated uncensored text-generation conversational zh en

Related

Same base model
arzaan789/qwen2.5-1.5b-uncensored 768 ElementMerc/qwen2.5-1.5b-uncensored 566 DeKodez/Qwen2.5-1.5B-Instruct-abliterated 504 sbussiso/Qwen2.5-1.5B-abliterated 278 ElementMerc/qwen2.5-1.5b-abliterated 274
Total size
4.41 GB
Files
9
Quantizations
1
Registered
2026-10-29 09:01
Last updated on HF
2026-10-29 06:50
Source huggingface.co/SonGT1/Qwen2.5-1.5B-Instruct-abliterated ↗ Base model Qwen/Qwen2.5-1.5B-Instruct ↗

Files by quantization

Auxiliary files 9 files 4.42 GB
model.safetensors 2.88 GB 7b58512e download
qwen2.5-1.5b-tria13-q8_0.gguf 1.53 GB a95d8aad download
tokenizer.json 10.9 MB 3fd16973 download
chat_template.jinja 2.50 KB 9840d40f download
.gitattributes 1.60 KB 3e30d9b8 download
config.json 1.40 KB 11f1c200 download
README.md 834 B a9c37a7d download
tokenizer_config.json 724 B df142d09 download
generation_config.json 256 B 367775e3 download

README current version from Hugging Face

license: apache-2.0
language:

  • zh
  • en
    base_model:
  • Qwen/Qwen2.5-1.5B-Instruct
    pipeline_tag: text-generation
    tags:
  • qwen2.5
  • chinese
  • English
  • abliterated
  • safetensors
  • gguf
  • uncensored
Refusal rate KL
8/100 0.0759

Acknowledgements

abliterated：heretic
Base model：Qwen/Qwen2.5-1.5B-Instruct

Disclaimer

Most safety guardrails of this model are removed. Generated content is unfiltered.
All generated content is the responsibility of the end user. The author takes no legal liability. Users must follow local laws.

本模型移除大部分安全护栏，输出无强制过滤。生成内容由使用者自行承担全部法律责任，作者不承担任何责任，请遵守当地法律。

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