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

Rupesh2/Llama-3.1-Uncensored-New

Rupesh2 Llama 8.0B 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/Rupesh2%2FLlama-3.1-Uncensored-New"
Response includes
  • classification m5
  • files 25
  • hub_downloads_all_time 217
  • author_summary 13 models
  • readme_text full
Try next
GET/models?author=Rupesh2
All 13 models by Rupesh2
 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

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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • no abliteration marker
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
217
19 last 30d - cooling
Likes
0
Descendants
2
in 2 direct forks
Model age
2.2y ago
created 2024-07-26
Downloads over time
Now224→from13↑1,623%
08216424613 on Jul 24, 2024224 on Oct 11224 on Oct 9Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Genealogy 2 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.

aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored↓ 124 this lineage
Rupesh2/Llama-3.1-Uncensored-New↓ 19 2 forks
mradermacher/Llama-3.1-Uncensored-New-i1-GGUF↓ 922
mradermacher/Llama-3.1-Uncensored-New-GGUF↓ 439

Metadata

Tags
transformers safetensors llama text-generation mergekit merge conversational base_model:Orenguteng/Llama-3-8B-Lexi-Uncensored base_model:merge:Orenguteng/Llama-3-8B-Lexi-Uncensored base_model:aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored base_model:merge:aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored text-generation-inference

Related

Other by Rupesh2
Llama-3.1-8B-Uncensored 83 Llama-3.1-8b-Uncensored-Dare 25 OrpoLlama-3-8B-uncensored 21 Meta-Llama-3-8B-uncensored 16 OrpoLlama-3-8B-instruct-uncensored 16
Same base model
bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-GGUF 4K mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-i1-GGUF 4K mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-GGUF 664 featherless-ai-quants/aifeifei798-DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-GGUF 604 MaziyarPanahi/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-GGUF 306
Total size
15.0 GB
Files
25
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-07-26 13:08
Source huggingface.co/Rupesh2/Llama-3.1-Uncensored-New ↗ Base model aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored →

Files by quantization

Auxiliary files 25 files 15.0 GB
model-00002-of-00017.safetensors 1002 MB 264ccb54 download
model-00001-of-00017.safetensors 1002 MB c5e943dc download
model-00005-of-00017.safetensors 952 MB 2ec95b7c download
model-00009-of-00017.safetensors 952 MB b9e225c6 download
model-00013-of-00017.safetensors 952 MB 2dc7acac download
model-00003-of-00017.safetensors 944 MB d601bd73 download
model-00004-of-00017.safetensors 944 MB 23ef109d download
model-00007-of-00017.safetensors 944 MB 20a61a1e download
model-00011-of-00017.safetensors 944 MB 13bd4a6a download
model-00012-of-00017.safetensors 944 MB 28d99881 download
model-00008-of-00017.safetensors 944 MB 45bb7fd3 download
model-00015-of-00017.safetensors 944 MB 1fc2dd47 download
model-00016-of-00017.safetensors 944 MB cea1672b download
model-00006-of-00017.safetensors 904 MB 8ba641a5 download
model-00010-of-00017.safetensors 904 MB 70dffba7 download
model-00014-of-00017.safetensors 904 MB 3b3d9a32 download
model-00017-of-00017.safetensors 192 MB caa77e2a download
tokenizer.json 8.66 MB 41280659 download
tokenizer_config.json 50.0 KB 02d8164d download
model.safetensors.index.json 22.3 KB 415e65c7 download
.gitattributes 1.48 KB a6344aac download
README.md 1.22 KB 2e660a49 download
config.json 935 B d8da8968 download
mergekit_config.yml 458 B 82f5649b download
special_tokens_map.json 439 B 344c8261 download

README current version from Hugging Face

base_model:

  • aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored
  • Orenguteng/Llama-3-8B-Lexi-Uncensored
    library_name: transformers
    tags:
  • mergekit
  • merge

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


slices:
  - sources:
      - model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored
        layer_range: [0, 32]
      - model: Orenguteng/Llama-3-8B-Lexi-Uncensored
        layer_range: [0, 32]
merge_method: slerp
base_model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

README history 1 version

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

  1. 2024-07-26Upload folder using huggingface_hub6dc92171.2 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