← back to catalog · registered 2026-08-22 13:56

netcat420/MFANN-abliterated-phi2-merge-unretrained

netcat420 Phi 2.8B
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/netcat420%2FMFANN-abliterated-phi2-merge-unretrained"
Response includes
  • classification m5
  • files 13
  • hub_downloads_all_time 1,664
  • author_summary 60 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • abliterated marker present
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 · lifetime
2K
27 last 30d - cooling
Likes
0
Descendants
1
in 1 direct fork
Model age
21mo ago
created 2025-01-15
Downloads over time
Now1.7K→from16↑10,413%
06161.2K1.8K16 on Jan 15, 20251.7K on Oct 111.7K on Oct 10Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 15, 2025 → Oct 11 · 130 snapshots · spans 634 days

Genealogy 1 direct fork

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

Tags
transformers safetensors phi text-generation mergekit merge conversational base_model:M1LL1X/microsoft-phi-2-trained-abliterated-QA-1960-all-modules-merged base_model:merge:M1LL1X/microsoft-phi-2-trained-abliterated-QA-1960-all-modules-merged base_model:netcat420/MFANN3bv1.1 base_model:merge:netcat420/MFANN3bv1.1 text-generation-inference

Related

Total size
5.17 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-01-15 03:37

Files by quantization

Auxiliary files 13 files 5.17 GB
model-00001-of-00002.safetensors 4.63 GB 46d09f60 download
model-00002-of-00002.safetensors 550 MB e7af287d download
tokenizer.json 3.40 MB 64f470fe download
vocab.json 779 KB 84ef7fb5 download
merges.txt 446 KB 226b0752 download
model.safetensors.index.json 33.1 KB 6a498fb4 download
tokenizer_config.json 8.05 KB abeaf8ab download
.gitattributes 1.48 KB a6344aac download
README.md 1.25 KB 98e34998 download
added_tokens.json 1.10 KB 3faee4f9 download
config.json 814 B cc528179 download
special_tokens_map.json 655 B 44719d2e download
mergekit_config.yml 494 B 25d7aa6f download

README current version from Hugging Face


base_model:

  • netcat420/MFANN3bv1.1
  • M1LL1X/microsoft-phi-2-trained-abliterated-QA-1960-all-modules-merged
    library_name: transformers
    tags:
  • mergekit
  • merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: M1LL1X/microsoft-phi-2-trained-abliterated-QA-1960-all-modules-merged
        layer_range: [0, 32]
      - model: netcat420/MFANN3bv1.1
        layer_range: [0, 32]
merge_method: slerp
base_model: M1LL1X/microsoft-phi-2-trained-abliterated-QA-1960-all-modules-merged
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: float16

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2025-01-15Upload folder using huggingface_hubcfc2d471.2 KB
    Loading...
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