← back to catalog · registered 2026-09-19 11:56

3MPER0RR/GLM-4.6V-Flash-Lora-adapter-3MPER0RR-abliterated

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/3MPER0RR%2FGLM-4.6V-Flash-Lora-adapter-3MPER0RR-abliterated"
Response includes
  • classification m1
  • files 4
  • author_summary 23 models
  • readme_text full
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-09-19

Metadata

Tags
peft safetensors base_model:adapter:GLM-4.6V-Flash-3MPER0RR-abliterated lora transformers base_model:3MPER0RR/GLM-4.6V-Flash-3MPER0RR-abliterated base_model:adapter:3MPER0RR/GLM-4.6V-Flash-3MPER0RR-abliterated license:mit region:us

Related

Total size
11.9 MB
Files
4
Quantizations
1
Registered
2026-09-19 11:56
Last updated on HF
2026-09-19 11:29

Files by quantization

Auxiliary files 4 files 11.9 MB
adapter_model.safetensors 11.9 MB 5219d32f download
adapter_config.json 2.14 KB 713e3cfe download
.gitattributes 1.48 KB a6344aac download
README.md 183 B d854a89e download

README current version from Hugging Face


license: mit
base_model:

  • 3MPER0RR/GLM-4.6V-Flash-3MPER0RR-abliterated
    library_name: peft
    tags:
  • base_model:adapter:GLM-4.6V-Flash-3MPER0RR-abliterated
  • lora
  • transformers

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.