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

huggingkot/NeuralDaredevil-8B-abliterated-bnb-4bit

huggingkot 7.2B second-order
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/huggingkot%2FNeuralDaredevil-8B-abliterated-bnb-4bit"
Response includes
  • classification m1
  • files 10
  • benchmarks 16 entries
  • hub_downloads_all_time 453
  • author_summary 8 models
  • readme_text full
Try next
GET/models?author=huggingkot
All 8 models by huggingkot
 GET/methods/m1
What "m1" means · taxonomy
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)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
453
15 last 30d - cooling
Likes
0
Model age
19mo ago
created 2025-03-12
Downloads over time
Now459→from4↑11,375%
01683365054 on Mar 12, 2025459 on Oct 11459 on Oct 7Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 12, 2025 → Oct 11 · 122 snapshots · spans 578 days

Benchmarks

Benchmark Score Source
BBH average 0.4680243870800363 OpenLLM-v2
IFEval instruct 0.7949640287769785 OpenLLM-v2
IFEval-Prompt 0.7171903881700554 OpenLLM-v2
MATH lvl 5 0.08006042296072508 OpenLLM-v2
MMLU-Pro 0.38414228723404253 OpenLLM-v2
Entertainment 1 UGI
Hazardous 2.9 UGI
Natural Intelligence 19.28 UGI
Political lean -13.8% UGI
Sensitive-Info 17.3 UGI
SocPol 1.6 UGI
UGI 33.2 UGI
Willingness (10) 6.5 UGI
W10-Adherence 7 UGI
W10-Direct 6 UGI
Writing 24.86 UGI

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

mlabonne/NeuralDaredevil-8B-abliterated↓ 15,130 this lineage
huggingkot/NeuralDaredevil-8B-abliterated-bnb-4bit↓ 15

Metadata

Tags
safetensors base_model:mlabonne/NeuralDaredevil-8B-abliterated base_model:finetune:mlabonne/NeuralDaredevil-8B-abliterated 8-bit region:us

Related

Other by huggingkot
Llama-3-8B-Instruct-abliterated-v2-bnb-4bit 327 Llama-3-8B-Instruct-abliterated-v2-Q4_K_M-GGUF 253 NeuralDaredevil-8B-abliterated-q4f16_1-MLC 96 dolphin-2.9.2-Phi-3-Medium-abliterated-Q4_K_M-GGUF 58 Llama-3-8B-Instruct-abliterated-v2-q4f16_1-MLC 23
Same base model
QuantFactory/NeuralDaredevil-8B-abliterated-GGUF 4K mradermacher/Daredevil-8B-abliterated-dpomix-i1-GGUF 2K mradermacher/Daredevil-8B-abliterated-dpomix-GGUF 1K mradermacher/NeuralDaredevil-8B-abliterated-i1-GGUF 1K featherless-ai-quants/mlabonne-NeuralDaredevil-8B-abliterated-GGUF 637
Total size
5.31 GB
Files
10
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-03-12 17:57
Source huggingface.co/huggingkot/NeuralDaredevil-8B-abliterated-bnb-4bit ↗ Base model mlabonne/NeuralDaredevil-8B-abliterated →

Files by quantization

Auxiliary files 10 files 5.33 GB
model-00001-of-00002.safetensors 4.33 GB 33a27b27 download
model-00002-of-00002.safetensors 1002 MB 2c17b8e3 download
tokenizer.json 16.4 MB 3c5cf440 download
model.safetensors.index.json 129 KB ecd55482 download
tokenizer_config.json 49.9 KB bb69dcac download
.gitattributes 1.53 KB c4cb545c download
config.json 1.17 KB eda4f92e download
README.md 882 B c5dbe13d download
special_tokens_map.json 350 B a40e70b6 download
generation_config.json 220 B c72858f1 download

README current version from Hugging Face

base_model:

  • mlabonne/NeuralDaredevil-8B-abliterated

This is a converted weight from NeuralDaredevil-8B-abliterated model in unsloth 4-bit dynamic quant using this collab notebook.

About this Conversion

This conversion uses Unsloth to load the model in 4-bit format and force-save it in the same 4-bit format.

How 4-bit Quantization Works

  • The actual 4-bit quantization is handled by BitsAndBytes (bnb), which works under Torch via AutoGPTQ or BitsAndBytes.
  • Unsloth acts as a wrapper, simplifying and optimizing the process for better efficiency.

This allows for reduced memory usage and faster inference while keeping the model compact.

README history 1 version

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

  1. 2025-03-12add files5981936882 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.

Get the app Browse the catalog
Open in Abliteration