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

seandearnaley/neuraldaredevil-8b-abliterated-sentiment-analysis-june-05-2024-1-epoch

seandearnaley Llama 8.0B GGUF second-order 8K ctx
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/seandearnaley%2Fneuraldaredevil-8b-abliterated-sentiment-analysis-june-05-2024-1-epoch"
Response includes
  • classification m8
  • files 16
  • benchmarks 16 entries
  • hub_downloads_all_time 4,376
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=llama&method=m8
Sibling llama models · same method
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
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=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
How we label → About M8 →
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
4K
330 last 30d - cooling
Likes
0
Model age
2.3y ago
created 2024-06-05
Downloads over time
Now4.5K→from173↑2,516%
01.7K3.3K5K173 on Jul 24, 20244.5K on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 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
seandearnaley/neuraldaredevil-8b-abliterated-sentiment-analysis-june-05-2024-1-epoch↓ 330

Metadata

License
apache-2.0
Languages
en
Quantizations
F16 Q4_K Q5_K Q8_0
Tags
transformers safetensors gguf llama text-generation-inference unsloth trl sft en arxiv:2405.18357 base_model:mlabonne/NeuralDaredevil-8B-abliterated base_model:quantized:mlabonne/NeuralDaredevil-8B-abliterated

Related

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
47.8 GB
Files
16
Quantizations
5
Registered
2026-08-22 13:56
Last updated on HF
2024-06-11 00:45
Source huggingface.co/seandearnaley/neuraldaredevil-8b-abliterated-sentiment-analysis-june-05-2024-1-epoch ↗ Base model mlabonne/NeuralDaredevil-8B-abliterated →

Files by quantization

F16 1 file 15.0 GB
neuraldaredevil-8b-abliterated-sentiment-analysis-june-05-2024-1-epoch-unsloth.F16.gguf 15.0 GB ba05cebc download
Q8_0 1 file 7.95 GB
neuraldaredevil-8b-abliterated-sentiment-analysis-june-05-2024-1-epoch-unsloth.Q8_0.gguf 7.95 GB 88d2235a download
Q5_K 1 file 5.34 GB
neuraldaredevil-8b-abliterated-sentiment-analysis-june-05-2024-1-epoch-unsloth.Q5_K_M.gguf 5.34 GB ac023b8c download
Q4_K 1 file 4.58 GB
neuraldaredevil-8b-abliterated-sentiment-analysis-june-05-2024-1-epoch-unsloth.Q4_K_M.gguf 4.58 GB 26da719a download
Auxiliary files 12 files 15.0 GB
model-00002-of-00004.safetensors 4.66 GB c9317ecb download
model-00001-of-00004.safetensors 4.63 GB fb3c801f download
model-00003-of-00004.safetensors 4.58 GB b84244e7 download
model-00004-of-00004.safetensors 1.09 GB 424e3f7e download
tokenizer.json 8.66 MB b197f72e download
tokenizer_config.json 50.0 KB be124938 download
model.safetensors.index.json 23.4 KB 0fd8120f download
.gitattributes 1.97 KB 59235c71 download
README.md 1.20 KB 49041ca3 download
special_tokens_map.json 350 B 9c44d1d7 download
generation_config.json 121 B f0ca288a download
config.json 29.0 B a4ba21b7 download

README current version from Hugging Face

language:

  • en
    license: apache-2.0
    tags:
  • text-generation-inference
  • transformers
  • unsloth
  • llama
  • trl
  • sft
    base_model: mlabonne/NeuralDaredevil-8B-abliterated

Sentiment Analysis Finetue

based on symbolic reasoning

dataset: https://huggingface.co/datasets/seandearnaley/symbolic_sentiment_v1

inspired by: https://arxiv.org/pdf/2405.18357

use this system instruction:

You are an advanced AI assistant created to perform sentiment analysis on text. Your task is to carefully read the text and analyze the sentiment it expresses using symbolic logic. Analyze the sentiment of this text and respond with the appropriate JSON:

see this link for free article:

Elevating Sentiment Analysis
https://medium.com/@seandearnaley/elevating-sentiment-analysis-ad02a316df1d

Uploaded model

  • Developed by: Sean Dearnaley
  • License: apache-2.0
  • Finetuned from model : mlabonne/NeuralDaredevil-8B-abliterated

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

README history 5 versions

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

  1. 2024-06-11Update README.md76897081.2 KB
    Loading...
  2. 2024-06-11Update README.md5920a151.2 KB
    Loading...
  3. 2024-06-11Update README.md9eaf34c1.1 KB
    Loading...
  4. 2024-06-05Trained with Unslothbfe5641610 B
    Loading...
  5. 2024-06-05Upload README.md with huggingface_hub6f05107604 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