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

skilledu/Dolphin3.0-Llama3.1-8B-abliterated

skilledu Llama 8.0B
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/skilledu%2FDolphin3.0-Llama3.1-8B-abliterated"
Response includes
  • classification m1
  • files 12
  • hub_downloads_all_time 1,034
  • author_summary 12 models
  • readme_text full
Try next
GET/models?author=skilledu
All 12 models by skilledu
 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
1K
169 last 30d - stable
Likes
1
Model age
5mo ago
created 2026-05-08
Downloads over time
Now1.1K→from8↑13,025%
03857691.2K8 on May 61.1K on Oct 11MayJunJulAugSepOct
May 6 → Oct 11 · 62 snapshots · spans 158 days

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.

cognitivecomputations/Dolphin3.0-Llama3.1-8B this lineage
skilledu/Dolphin3.0-Llama3.1-8B-abliterated↓ 169

Metadata

License
llama3.1
Languages
en
Tags
transformers safetensors llama text-generation abliterated uncensored conversational en base_model:dphn/Dolphin3.0-Llama3.1-8B base_model:finetune:dphn/Dolphin3.0-Llama3.1-8B license:llama3.1 text-generation-inference

Related

Other by skilledu
Dirty-Muse-Writer-v01-Uncensored-Erotica-NSFW-i1-GGUF 991 Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive 289 Qwen2.5-Coder-3B-Instruct-abliterated 135 Meta-Llama-3-8B-Instruct-abliterated-v3-GGUF 135 Qwen3.5-9B-abliterated 24
Total size
15.0 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-05-08 06:53
Source huggingface.co/skilledu/Dolphin3.0-Llama3.1-8B-abliterated ↗ Base model cognitivecomputations/Dolphin3.0-Llama3.1-8B ↗

Files by quantization

Auxiliary files 12 files 15.0 GB
model-00002-of-00004.safetensors 4.66 GB b322bfd8 download
model-00001-of-00004.safetensors 4.63 GB fb7eed7c download
model-00003-of-00004.safetensors 4.58 GB 00610048 download
model-00004-of-00004.safetensors 1.09 GB 09c54951 download
tokenizer.json 16.4 MB cca43616 download
tokenizer_config.json 52.1 KB b754ae22 download
model.safetensors.index.json 23.7 KB 14c7a5d3 download
.gitattributes 1.53 KB 52373fe2 download
config.json 902 B cc74b653 download
README.md 813 B 8f710327 download
special_tokens_map.json 467 B 6a9ba8de download
generation_config.json 215 B d764fe08 download

README current version from Hugging Face

license: llama3.1
language:

  • en
    tags:
  • abliterated
  • uncensored
    base_model:
  • cognitivecomputations/Dolphin3.0-Llama3.1-8B
    library_name: transformers

huihui-ai/Dolphin3.0-Llama3.1-8B-abliterated

This is an uncensored version of cognitivecomputations/Dolphin3.0-Llama3.1-8B created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

Use with ollama

You can use huihui_ai/dolphin3-abliterated directly

ollama run huihui_ai/dolphin3-abliterated

README history 1 version

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

  1. 2026-05-08Duplicate from huihui-ai/Dolphin3.0-Llama3.1-8B-abliterated55ecda6813 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