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

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

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/3MPER0RR%2FGLM-4.6V-Flash-3MPER0RR-abliterated"
Response includes
  • classification m1
  • files 14
  • 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

License
mit
Tags
safetensors glm4v text-generation conversational license:mit region:us

Related

Total size
19.2 GB
Files
14
Quantizations
1
Registered
2026-09-19 11:56
Last updated on HF
2026-09-19 11:12

Files by quantization

Auxiliary files 14 files 19.2 GB
model-00004-of-00005.safetensors 4.65 GB 7bc633e1 download
model-00001-of-00005.safetensors 4.59 GB bc3840a3 download
model-00003-of-00005.safetensors 4.56 GB 623e9332 download
model-00002-of-00005.safetensors 4.56 GB bc874faa download
model-00005-of-00005.safetensors 834 MB 656c2477 download
tokenizer.json 19.0 MB bda8e214 download
model.safetensors.index.json 64.9 KB 3d7a7cec download
chat_template.jinja 4.50 KB efe6364a download
config.json 1.59 KB ba64b60e download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.30 KB b14e663a download
tokenizer_config.json 949 B 4df38535 download
generation_config.json 240 B c888c3ed download
README.md 225 B 5636a358 download

README current version from Hugging Face


license: mit
pipeline_tag: text-generation

Model: GLM-4.6V-Flash

Process: Multi-round abliteration

Status: Tested and saved

Original model: GLM-4.6V-Flash

License: [Mit]

Research and experimentation by [3MPER0RR]

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.