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

v000000/Llama-3.1-8B-Stheno-v3.4-abliterated

v000000 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/v000000%2FLlama-3.1-8B-Stheno-v3.4-abliterated"
Response includes
  • classification m5
  • files 15
  • hub_downloads_all_time 635
  • author_summary 5 models
  • readme_text full
Try next
GET/models?author=v000000
All 5 models by v000000
 GET/models?family=llama&method=m5
Sibling llama models · same method
 GET/methods/m5
What "m5" means · taxonomy
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
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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • abliterated marker present
How we label → About M5 →
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
635
27 last 30d - cooling
Likes
5
Descendants
3
in 3 direct forks
Model age
2.1y ago
created 2024-08-23
Downloads over time
Now647→from12↑5,292%
023747471112 on Aug 21, 2024647 on Oct 11647 on Oct 9Aug '24Dec '24Apr '25Aug '25Dec '25AprAug
Aug 21, 2024 → Oct 11 · 151 snapshots · spans 781 days

Genealogy 3 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.

Sao10K/Llama-3.1-8B-Stheno-v3.4 this lineage
v000000/Llama-3.1-8B-Stheno-v3.4-abliterated↓ 27 3 forks
mradermacher/Llama-3.1-8B-Stheno-v3.4-abliterated-i1-GGUF↓ 2,015
mradermacher/Llama-3.1-8B-Stheno-v3.4-abliterated-GGUF↓ 895
v000000/Llama-3.1-8B-Stheno-v3.4-abliterated-GGUF↓ 77

Variants by this author 2 formats · 104 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Tags
transformers safetensors llama text-generation mergekit merge conversational arxiv:2203.05482 base_model:Sao10K/Llama-3.1-8B-Stheno-v3.4 base_model:merge:Sao10K/Llama-3.1-8B-Stheno-v3.4 base_model:grimjim/Llama-3-Instruct-abliteration-LoRA-8B base_model:merge:grimjim/Llama-3-Instruct-abliteration-LoRA-8B

Related

Other by v000000
Llama-3.1-8B-Stheno-v3.4-abliterated-GGUF 77 SwallowMaid-8B-L3-SPPO-abliterated 60 L3-8B-Stheno-v3.2-abliterated 36 SwallowMaid-8B-L3-SPPO-abliterated-Q8_0-GGUF 27
Total size
29.9 GB
Files
15
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-08-23 09:00
Source huggingface.co/v000000/Llama-3.1-8B-Stheno-v3.4-abliterated ↗ Base model Sao10K/Llama-3.1-8B-Stheno-v3.4 ↗

Files by quantization

Auxiliary files 15 files 29.9 GB
model-00003-of-00007.safetensors 4.66 GB 4013f317 download
model-00004-of-00007.safetensors 4.66 GB c2c5374e download
model-00006-of-00007.safetensors 4.66 GB 43c2c80a download
model-00001-of-00007.safetensors 4.65 GB 60813a1c download
model-00002-of-00007.safetensors 4.58 GB e996af93 download
model-00005-of-00007.safetensors 4.50 GB 82932592 download
model-00007-of-00007.safetensors 2.22 GB 878a0b12 download
tokenizer.json 8.66 MB 5cc5f00a download
tokenizer_config.json 50.0 KB a2eb5bdc download
model.safetensors.index.json 22.3 KB eeeab3a7 download
.gitattributes 1.48 KB a6344aac download
README.md 1.45 KB b4e2f63d download
config.json 874 B 09252cad download
special_tokens_map.json 454 B 3c1d0491 download
mergekit_config.yml 166 B 4a4ae0d3 download

README current version from Hugging Face

base_model:

  • Sao10K/Llama-3.1-8B-Stheno-v3.4
  • grimjim/Llama-3-Instruct-abliteration-LoRA-8B
    library_name: transformers
    tags:
  • mergekit
  • merge
  • llama

Simply "Llama3.1-Stheno-v3.4" by Sao10K with abliteration adaption from grimjim

Thanks mradermacher for the quants.

Quant

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the linear 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: Sao10K/Llama-3.1-8B-Stheno-v3.4+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
    parameters:
      weight: 1.0
merge_method: linear
dtype: float32

README history 4 versions

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

  1. 2024-08-23Update README.mdc8752b31.4 KB
    Loading...
  2. 2024-08-23Update README.mda388ae11.2 KB
    Loading...
  3. 2024-08-23Update README.md47fe1dc1.1 KB
    Loading...
  4. 2024-08-23Upload folder using huggingface_hub6362655943 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