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

Dogge/llama-3-70B-instruct-uncensored-lora

Dogge Llama 70B
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/Dogge%2Fllama-3-70B-instruct-uncensored-lora"
Response includes
  • classification m-uncensored
  • files 9
  • hub_downloads_all_time 13,047
  • author_summary 4 models
  • readme_text full
Try next
GET/models?author=Dogge
All 4 models by Dogge
 GET/models?family=llama&method=m-uncensored
Sibling llama models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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
13K
25 last 30d - cooling
Likes
3
Model age
2.5y ago
created 2024-04-19
Downloads over time
Now13.1K→from347↑3,663%
04.8K9.6K14.4K347 on Jul 24, 202413.1K on Oct 1113.1K on Oct 8Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 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.

unsloth/llama-3-70b-Instruct-bnb-4bit this lineage
Dogge/llama-3-70B-instruct-uncensored-lora↓ 25

Metadata

License
apache-2.0
Languages
en
Tags
transformers safetensors llama text-generation text-generation-inference unsloth trl conversational en base_model:unsloth/llama-3-70b-Instruct-bnb-4bit base_model:quantized:unsloth/llama-3-70b-Instruct-bnb-4bit license:apache-2.0

Related

Other by Dogge
llama-3-70B-instruct-uncensored 36 llama-3-70B-uncensored 28 llama-3-70B-instruct-uncensored-4bit 14
Same base model
Dogge/llama-3-70B-instruct-uncensored 36 Dogge/llama-3-70B-instruct-uncensored-4bit 14
Total size
790 MB
Files
9
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-04-20 12:45
Source huggingface.co/Dogge/llama-3-70B-instruct-uncensored-lora ↗ Base model unsloth/llama-3-70b-Instruct-bnb-4bit ↗

Files by quantization

Auxiliary files 9 files 799 MB
adapter_model.safetensors 790 MB 327b380a download
tokenizer.json 8.66 MB 04e5f1d2 download
tokenizer_config.json 49.8 KB 242446c4 download
.gitattributes 1.48 KB a6344aac download
config.json 1.10 KB 1d1517a5 download
adapter_config.json 742 B 07932cc6 download
README.md 592 B 399a7b0b download
special_tokens_map.json 449 B e5b39b63 download
generation_config.json 121 B 08510f67 download

README current version from Hugging Face

language:

  • en
    license: apache-2.0
    tags:
  • text-generation-inference
  • transformers
  • unsloth
  • llama
  • trl
    base_model: unsloth/llama-3-70b-Instruct-bnb-4bit

Uploaded model

  • Developed by: Dogge
  • License: apache-2.0
  • Finetuned from model : unsloth/llama-3-70b-Instruct-bnb-4bit

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

README history 1 version

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

  1. 2024-04-19Upload README.md with huggingface_hub879cbac592 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