← back to catalog · registered 2026-11-21 09:04

lecheyne24/qwen2.5-coder-7b-abliterated

lecheyne24 Qwen 7B 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/lecheyne24%2Fqwen2.5-coder-7b-abliterated"
Response includes
  • classification m8
  • files 4
  • benchmarks 16 entries
  • author_summary 6 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 · 30-day
0
Likes
0
Model age
2d ago
created 2026-11-20

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
BBH average 0.4571280321701907 OpenLLM-v2
IFEval instruct 0.6546762589928058 OpenLLM-v2
IFEval-Prompt 0.5656192236598891 OpenLLM-v2
MATH lvl 5 0.033987915407854986 OpenLLM-v2
MMLU-Pro 0.3351894946808511 OpenLLM-v2
Entertainment 1 UGI
Hazardous 1.2 UGI
Natural Intelligence 13.97 UGI
Political lean -19.6% UGI
Sensitive-Info 7.29 UGI
SocPol 0 UGI
UGI 9.86 UGI
Willingness (10) 1.5 UGI
W10-Adherence 0 UGI
W10-Direct 3 UGI
Writing 18.77 UGI

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.

Metadata

Quantizations
Q4_K
Tags
llama.cpp gguf abliterated uncensored qwen2.5-coder code text-generation base_model:Qwen/Qwen2.5-Coder-7B-Instruct base_model:quantized:Qwen/Qwen2.5-Coder-7B-Instruct endpoints_compatible region:us conversational

Related

Total size
8.72 GB
Files
4
Quantizations
2
Registered
2026-11-21 09:04
Last updated on HF
2026-11-21 07:53

Files by quantization

Q4_K 2 files 8.72 GB
Qwen2.5-Coder-7B-Instruct-abliterated.Q4_K_M.gguf 4.36 GB ae9f2a4b download
qwen2.5-coder-7b-unbound.Q4_K_M.gguf 4.36 GB cee6c10d download
Auxiliary files 2 files 2.36 KB
.gitattributes 1.64 KB 9a9cf78a download
README.md 738 B 4b36584e download

README current version from Hugging Face


base_model: Qwen/Qwen2.5-Coder-7B-Instruct
library_name: llama.cpp
tags:

  • abliterated
  • uncensored
  • gguf
  • qwen2.5-coder
  • code
  • text-generation
    quantized_by: lecheyne24

qwen2.5-coder-7b-abliterated (Q4_K_M, GGUF)

Uncensored build of Qwen/Qwen2.5-Coder-7B-Instruct.

  • Method: refusal-direction rank-1 norm-preserving biprojection (o_proj + down_proj), alpha 1.25, all layers.
  • Quant: Q4_K_M
  • Files: Qwen2.5-Coder-7B-Instruct-abliterated.Q4_K_M.gguf, qwen2.5-coder-7b-unbound.Q4_K_M.gguf
  • Plain-answer gauntlet: 8/8. Strong general verdict posture for a coder base.

Run

llama-server -m Qwen2.5-Coder-7B-Instruct-abliterated.Q4_K_M.gguf --port 8083 -c 4096 --alias qwen2.5-coder-7b
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