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

Sorawiz/Phi-4-Empathetic-Abliterated

Sorawiz Phi 15B
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/Sorawiz%2FPhi-4-Empathetic-Abliterated"
Response includes
  • classification m5
  • files 16
  • hub_downloads_all_time 80
  • author_summary 2 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
80
17 last 30d - stable
Likes
2
Descendants
1
in 1 direct fork
Model age
20mo ago
created 2025-01-20
Downloads over time
Now89→from0↑0%
01112223330 on Jan 15, 202589 on Oct 11303 on Sep 24, 2025Jan '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 llama text-generation mergekit merge conversational base_model:ngxson/LoRA-phi-4-abliterated base_model:merge:ngxson/LoRA-phi-4-abliterated base_model:prithivMLmods/Phi-4-Empathetic base_model:merge:prithivMLmods/Phi-4-Empathetic text-generation-inference

Related

Total size
27.3 GB
Files
16
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-01-20 14:39

Files by quantization

Auxiliary files 16 files 27.3 GB
model-00003-of-00006.safetensors 4.63 GB 0b3f8220 download
model-00001-of-00006.safetensors 4.62 GB 9a6a4909 download
model-00002-of-00006.safetensors 4.61 GB d5cd43df download
model-00005-of-00006.safetensors 4.61 GB e271709f download
model-00004-of-00006.safetensors 4.55 GB b75d537c download
model-00006-of-00006.safetensors 4.27 GB 246378a3 download
tokenizer.json 6.82 MB 0f36bbc9 download
vocab.json 1.54 MB c5dc46ce download
merges.txt 895 KB 354558ed download
model.safetensors.index.json 27.8 KB 071fe705 download
tokenizer_config.json 17.6 KB a85152c4 download
.gitattributes 1.48 KB a6344aac download
README.md 816 B dbb7b9cd download
config.json 813 B 815de399 download
special_tokens_map.json 570 B 592153e4 download
mergekit_config.yml 121 B a4ab35ac download

README current version from Hugging Face


base_model:

  • prithivMLmods/Phi-4-Empathetic
  • ngxson/LoRA-phi-4-abliterated
    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 passthrough merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: prithivMLmods/Phi-4-Empathetic+ngxson/LoRA-phi-4-abliterated
merge_method: passthrough
dtype: bfloat16

README history 1 version

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

  1. 2025-01-20Upload folder using huggingface_hubd1ed280816 B
    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