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

digitalpipelines/llama2_13b_chat_uncensored

digitalpipelines Llama
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/digitalpipelines%2Fllama2_13b_chat_uncensored"
Response includes
  • classification m-uncensored
  • files 15
  • hub_downloads_all_time 369
  • author_summary 6 models
  • readme_text full
Try next
GET/models?author=digitalpipelines
All 6 models by digitalpipelines
 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
369
19 last 30d - cooling
Likes
0
Model age
3.1y ago
created 2023-08-18

Training datasets

1 of 1 in /datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

digitalpipelines/wizard_vicuna_70k_uncensored fine-tune
Downloads over time
Now375→from7↑5,257%
01372754127 on Jul 24, 2024375 on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Variants by this author 2 formats · 39 downloads combined

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

Metadata

License
llama2
Tags
transformers pytorch llama text-generation uncensored wizard vicuna dataset:digitalpipelines/wizard_vicuna_70k_uncensored license:llama2 text-generation-inference endpoints_compatible region:us

Related

Other by digitalpipelines
llama2_7b_chat_uncensored-GPTQ 27 llama2_13b_chat_uncensored-GPTQ 20 llama2_7b_chat_uncensored 19 llama2_7b_chat_uncensored-GGML 0 llama2_13b_chat_uncensored-GGML 0
Total size
48.5 GB
Files
15
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2023-08-21 17:04
Source huggingface.co/digitalpipelines/llama2_13b_chat_uncensored ↗

Files by quantization

Auxiliary files 15 files 48.5 GB
pytorch_model-00001-of-00006.bin 9.27 GB 63925445 download
pytorch_model-00003-of-00006.bin 9.26 GB 86e653a8 download
pytorch_model-00002-of-00006.bin 9.26 GB 97dccdbd download
pytorch_model-00005-of-00006.bin 9.19 GB 49f9465a download
pytorch_model-00004-of-00006.bin 9.19 GB b46cf6e3 download
pytorch_model-00006-of-00006.bin 2.32 GB a2f32cdf download
tokenizer.model 488 KB 9e556afd download
pytorch_model.bin.index.json 32.7 KB 4d43393c download
README.md 1.82 KB 91698ee5 download
.gitattributes 1.48 KB a6344aac download
tokenizer_config.json 745 B 1e4fd8d4 download
config.json 631 B b1558a6b download
special_tokens_map.json 435 B 599f3bbf download
generation_config.json 132 B 2b103309 download
added_tokens.json 21.0 B e41416dd download

README current version from Hugging Face

license: llama2
datasets:

  • digitalpipelines/wizard_vicuna_70k_uncensored
    tags:
  • uncensored
  • wizard
  • vicuna
  • llama
Digital Pipelines

Overview

Fine-tuned Llama-2 13B trained with an uncensored/unfiltered Wizard-Vicuna conversation dataset digitalpipelines/wizard_vicuna_70k_uncensored.
A QLoRA was created and used for fine-tuning and then merged back into the model. Llama2 has inherited bias even though it's been finetuned on an uncensored dataset.

Available versions of this model

Prompt template: Llama-2-Chat

SYSTEM: You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
USER: {prompt}
ASSISTANT:

README history 3 versions

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

  1. 2023-08-21Update README.mde64bf5c1.8 KB
    Loading...
  2. 2023-08-21Update README.mdd8b55591.7 KB
    Loading...
  3. 2023-08-21Create README.md00466541.7 KB
    Loading...

Discussions 2 threads

  1. 2025-06-17PRAdding `safetensors` variant of this modelopen1 💬#2
    Loading...
  2. 2023-08-29Model has serious censorshipclosed2 💬#1
    Loading...

Continue on Hugging Face →

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