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

mergekit-community/Llama-3-ThinkRoleplay-DeepSeek-R1-Distill-8B-abliterated

mergekit-community 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/mergekit-community%2FLlama-3-ThinkRoleplay-DeepSeek-R1-Distill-8B-abliterated"
Response includes
  • classification m5
  • files 12
  • hub_downloads_all_time 137
  • author_summary 6 models
  • readme_text full
Try next
GET/models?author=mergekit-community
All 6 models by mergekit-community
 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
137
29 last 30d - stable
Likes
1
Descendants
2
in 2 direct forks
Model age
20mo ago
created 2025-02-05
Downloads over time
Now153→from12↑1,175%
55911316712 on Feb 5, 2025153 on Oct 11153 on Oct 10Feb '25May '25Aug '25Nov '25FebMayAug
Feb 5, 2025 → Oct 11 · 127 snapshots · spans 613 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.

huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated↓ 711 this lineage
mergekit-community/Llama-3-ThinkRoleplay-DeepSeek-R1-Distill-8B-abliterated↓ 29 2 forks
mradermacher/Llama-3-ThinkRoleplay-DeepSeek-R1-Distill-8B-abliterated-i1-GGUF↓ 896
mradermacher/Llama-3-ThinkRoleplay-DeepSeek-R1-Distill-8B-abliterated-GGUF↓ 279

Metadata

Tags
transformers safetensors llama text-generation mergekit merge conversational arxiv:2311.03099 base_model:Azazelle/Llama-3-8B-contaminated-roleplay base_model:merge:Azazelle/Llama-3-8B-contaminated-roleplay base_model:huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated base_model:merge:huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated

Related

Other by mergekit-community
Llama-3-DeepSeek-R1-Distill-8B-LewdPlay-Uncensored 239 Llama-3-LewdPlay-DeepSeek-R1-Distill-8B-abliterated 24 Tigers-Abliterated-9B 20 uncensored-mix 18 Tigers-Abliterated-Upscaled 13
Same base model
cstr/DeepSeek-R1-Distill-Llama-8B-abliterated-Q4_K_M-GGUF 746 tensorblock/DeepSeek-R1-Distill-Llama-8B-abliterated-GGUF 287 PocketWeights/DeepSeek-R1-Llama-8B-Abliterated-GGUF 205 maicog/DeepSeek-R1-Distill-Llama-8B-abliterated-Q4_K_S-GGUF 174 AlfRjw/DeepSeek-R1-Distill-Llama-8B-abliterated-Q4-mlx 45
Total size
15.0 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-02-05 18:39
Source huggingface.co/mergekit-community/Llama-3-ThinkRoleplay-DeepSeek-R1-Distill-8B-abliterated ↗ Base model huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated →

Files by quantization

Auxiliary files 12 files 15.0 GB
model-00002-of-00004.safetensors 4.66 GB 36da9027 download
model-00001-of-00004.safetensors 4.61 GB 5e8fac4c download
model-00003-of-00004.safetensors 4.58 GB 013ca239 download
model-00004-of-00004.safetensors 1.11 GB 2c029a91 download
tokenizer.json 16.4 MB 0968dcc0 download
tokenizer_config.json 49.8 KB 12e87e92 download
model.safetensors.index.json 22.3 KB 6211a1b2 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.20 KB b9985404 download
config.json 754 B c12082bc download
special_tokens_map.json 449 B e5b39b63 download
mergekit_config.yml 387 B 9808e070 download

README current version from Hugging Face

base_model:

  • huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated
  • Azazelle/Llama-3-8B-contaminated-roleplay
    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 DARE TIES merge method using Azazelle/Llama-3-8B-contaminated-roleplay as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

  models:
    - model: Azazelle/Llama-3-8B-contaminated-roleplay
      # No parameters necessary for base model
    - model: huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated
      parameters:
        density: 0.53
        weight: 0.6
  merge_method: dare_ties
  base_model: Azazelle/Llama-3-8B-contaminated-roleplay
  parameters:
    int8_mask: true
  dtype: bfloat16
  random_seed: 42

README history 1 version

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

  1. 2025-02-05Upload folder using huggingface_hubb0f45461.2 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