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

Zoyd/mlabonne_NeuralDaredevil-8B-abliterated-3_75bpw_exl2

Zoyd Llama 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/Zoyd%2Fmlabonne_NeuralDaredevil-8B-abliterated-3_75bpw_exl2"
Response includes
  • classification m1
  • files 9
  • hub_downloads_all_time 46
  • author_summary 77 models
  • readme_text full
Try next
GET/models?author=Zoyd
All 77 models by Zoyd
 GET/models?family=llama&method=m1
Sibling llama models · same method
 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
46
13 last 30d - stable
Likes
0
Model age
2.4y ago
created 2024-05-28

Training datasets

1 of 1 in /datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

mlabonne/orpo-dpo-mix-40k heal
Downloads over time
Now52→from8↑550%
046921398 on Jul 24, 202452 on Oct 11126 on Sep 17, 2025Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Metadata

License
other
Tags
transformers safetensors llama text-generation dpo dataset:mlabonne/orpo-dpo-mix-40k license:other text-generation-inference endpoints_compatible exl2 region:us

Related

Other by Zoyd
mlabonne_NeuralDaredevil-8B-abliterated-4_0bpw_exl2 26 failspy_Phi-3-medium-4k-instruct-abliterated-v3-3_5bpw_exl2 25 failspy_Phi-3-medium-4k-instruct-abliterated-v3-4_0bpw_exl2 24 failspy_Phi-3-medium-4k-instruct-abliterated-v3-6_5bpw_exl2 24 mlabonne_Llama-3-8B-Instruct-abliterated-dpomix-5_0bpw_exl2 22
Total size
4.41 GB
Files
9
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-05-28 16:13
Source huggingface.co/Zoyd/mlabonne_NeuralDaredevil-8B-abliterated-3_75bpw_exl2 ↗

Files by quantization

Auxiliary files 9 files 4.42 GB
output.safetensors 4.41 GB f324671e download
tokenizer.json 8.66 MB b197f72e download
tokenizer_config.json 49.4 KB 72193e9e download
model.safetensors.index.json 23.4 KB 0fd8120f download
README.md 4.27 KB 11b6fe00 download
.gitattributes 1.48 KB a6344aac download
config.json 1.02 KB d5e5ebe6 download
special_tokens_map.json 301 B cfabacc2 download
generation_config.json 121 B b70403ad download

README current version from Hugging Face

license: other
datasets:

  • mlabonne/orpo-dpo-mix-40k
    tags:
  • dpo

Exllamav2 quant (exl2 / 3.75 bpw) made with ExLlamaV2 v0.1.1

Other EXL2 quants:

Quant Model Size lm_head
2.2
3250 MB
6
2.5
3479 MB
6
3.0
3895 MB
6
3.5
4310 MB
6
3.75
4519 MB
6
4.0
4727 MB
6
4.25
4931 MB
6
5.0
5559 MB
6
6.0
6495 MB
8
6.5
6903 MB
8
8.0
8157 MB
8

NeuralDaredevil-8B-abliterated

image/jpeg

This is a DPO fine-tune of mlabonne/Daredevil-8-abliterated trained on one epoch of mlabonne/orpo-dpo-mix-40k.

🏆 Evaluation

Open LLM Leaderboard

TBD.

Nous

Evaluation performed using LLM AutoEval. See the entire leaderboard here.

Model Average AGIEval GPT4All TruthfulQA Bigbench
mlabonne/NeuralDaredevil-8B-abliterated 📄 55.87 43.73 73.6 59.36 46.8
mlabonne/Daredevil-8B 📄 55.87 44.13 73.52 59.05 46.77
mlabonne/Daredevil-8B-abliterated 📄 55.06 43.29 73.33 57.47 46.17
NousResearch/Hermes-2-Theta-Llama-3-8B 📄 54.28 43.9 72.62 56.36 44.23
openchat/openchat-3.6-8b-20240522 📄 53.49 44.03 73.67 49.78 46.48
meta-llama/Meta-Llama-3-8B-Instruct 📄 51.34 41.22 69.86 51.65 42.64
meta-llama/Meta-Llama-3-8B 📄 45.42 31.1 69.95 43.91 36.7

🌳 Model family tree

image/png

README history 2 versions

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

  1. 2024-05-28Upload folder using huggingface_hubb54f0d64.3 KB
    Loading...
  2. 2024-05-28Upload folder using huggingface_hub9904e5b2.4 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.

Get the app Browse the catalog
Open in Abliteration