← back to catalog · registered 2026-09-18 22:56

DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3

DuoNeural 8B MoE
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/DuoNeural%2FLFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3"
Response includes
  • classification m1
  • files 7
  • author_summary 45 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 2026-09-18

Variants by this author 2 formats · 0 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Tags
safetensors lfm2_moe region:us

Related

Total size
15.8 GB
Files
7
Quantizations
1
Registered
2026-09-18 22:56
Last updated on HF
2026-09-18 22:10

Files by quantization

Auxiliary files 7 files 15.8 GB
model.safetensors 15.8 GB f12a30e9 download
tokenizer.json 17.1 MB 4e241348 download
chat_template.jinja 1.63 KB 64c58d03 download
.gitattributes 1.53 KB 52373fe2 download
config.json 1.18 KB fa4d8666 download
tokenizer_config.json 453 B 6b209abe download
generation_config.json 231 B 271bd4b6 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.