← back to catalog · registered 2026-09-17 08:56

Spikejester/Qwen2.5-Coder-1.5B-abliterated-Q2_K

Spikejester 1.5B GGUF
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
today
created 2026-09-17

Metadata

Quantizations
Q2_K
Tags
gguf endpoints_compatible region:us imatrix conversational
Total size
718 MB
Files
2
Quantizations
2
Registered
2026-09-17 08:56
Last updated on HF
2026-09-17 07:02

Files by quantization

Q2_K 1 file 718 MB
Qwen2.5-Coder-1.5B-Instruct-abliterated-Q2_K.gguf 718 MB 9a7b865a download
Auxiliary files 1 file 1.57 KB
.gitattributes 1.57 KB b95c9c39 download

README

The author did not publish a README.

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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.