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

Justbackup/Llama-3.3-70B-Instruct-abliterated

Justbackup Llama 71B
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/Justbackup%2FLlama-3.3-70B-Instruct-abliterated"
Response includes
  • classification m1
  • files 40
  • benchmarks 21 entries
  • hub_downloads_all_time 737
  • author_summary 30 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

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.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
737
41 last 30d - cooling
Likes
0
Model age
7w ago
created 2026-08-18
Downloads over time
Now748→from614↑22%
607659710761614 on Aug 19748 on Oct 11748 on Oct 7AugSepOct
Aug 19 → Oct 11 · 48 snapshots · spans 53 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Arena-Battles 54380 LM-Arena
LM Arena Elo 1278.472867347656 LM-Arena
Arena-Elo-Lower 1275.1639218994935 LM-Arena
Arena-Elo-Upper 1281.7818127958183 LM-Arena
Arena-Rank 93 LM-Arena
BBH average 0.6112336230380075 OpenLLM-v2
IFEval instruct 0.919664268585132 OpenLLM-v2
IFEval-Prompt 0.8798521256931608 OpenLLM-v2
MATH lvl 5 0.0022658610271903325 OpenLLM-v2
MMLU-Pro 0.5331615691489362 OpenLLM-v2
Entertainment 3.2 UGI
Hazardous 3.5 UGI
Natural Intelligence 31.37 UGI
Political lean -18.6% UGI
Sensitive-Info 36.83 UGI
SocPol 4.3 UGI
UGI 37.89 UGI
Willingness (10) 4 UGI
W10-Adherence 3 UGI
W10-Direct 5 UGI
Writing 26.18 UGI

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.

Variants by this author 3 formats · 674 downloads combined

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

Metadata

License
llama3.3
Languages
en fr it pt hi es th de
Tags
transformers safetensors llama text-generation facebook meta pytorch llama-3 abliterated uncensored conversational en

Related

Total size
131 GB
Files
40
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-18 16:20

Files by quantization

Auxiliary files 40 files 131 GB
model-00008-of-00030.safetensors 4.66 GB 4a436fa7 download
model-00013-of-00030.safetensors 4.66 GB 3529dd19 download
model-00018-of-00030.safetensors 4.66 GB 25f07149 download
model-00023-of-00030.safetensors 4.66 GB 89aba554 download
model-00028-of-00030.safetensors 4.66 GB 181ec0b8 download
model-00003-of-00030.safetensors 4.66 GB 2c1f77c1 download
model-00029-of-00030.safetensors 4.63 GB de4b6e30 download
model-00009-of-00030.safetensors 4.63 GB 411229ce download
model-00014-of-00030.safetensors 4.63 GB 192ba98a download
model-00019-of-00030.safetensors 4.63 GB 4aed6fc5 download
model-00024-of-00030.safetensors 4.63 GB b2ec885c download
model-00004-of-00030.safetensors 4.63 GB b8202206 download
model-00006-of-00030.safetensors 4.34 GB 20efd0e0 download
model-00007-of-00030.safetensors 4.34 GB 491644af download
model-00011-of-00030.safetensors 4.34 GB c8cd0ee9 download
model-00012-of-00030.safetensors 4.34 GB 804f259d download
model-00016-of-00030.safetensors 4.34 GB 28b6a15b download
model-00017-of-00030.safetensors 4.34 GB caaf04a6 download
model-00021-of-00030.safetensors 4.34 GB 99f169e8 download
model-00022-of-00030.safetensors 4.34 GB 8527ba8c download
model-00026-of-00030.safetensors 4.34 GB db615618 download
model-00027-of-00030.safetensors 4.34 GB a4bb1b48 download
model-00002-of-00030.safetensors 4.34 GB 321bb956 download
model-00005-of-00030.safetensors 4.34 GB fdec4ceb download
model-00010-of-00030.safetensors 4.34 GB 58918171 download
model-00015-of-00030.safetensors 4.34 GB 6e72da9a download
model-00020-of-00030.safetensors 4.34 GB a5c9da77 download
model-00025-of-00030.safetensors 4.34 GB 00bd2770 download
model-00001-of-00030.safetensors 4.27 GB ecc71fd0 download
model-00030-of-00030.safetensors 1.96 GB b0436c98 download
tokenizer.json 16.4 MB 6b9e4e7f download
model.safetensors.index.json 58.9 KB 6fdd1b8d download
tokenizer_config.json 56.1 KB f9ebcf6e download
README.md 16.1 KB 2ed8f6e1 download
LICENSE 7.72 KB 2c97b69e download
USE_POLICY.md 5.88 KB 2b5602b4 download
.gitattributes 1.53 KB 52373fe2 download
config.json 879 B adf1f490 download
special_tokens_map.json 477 B 2969fb88 download
generation_config.json 196 B f5f7a96d download

README current version from Hugging Face


library_name: transformers
language:

  • en
  • fr
  • it
  • pt
  • hi
  • es
  • th
  • de
    base_model:
  • meta-llama/Llama-3.3-70B-Instruct
    tags:
  • facebook
  • meta
  • pytorch
  • llama
  • llama-3
  • abliterated
  • uncensored
    extra_gated_prompt: "### LLAMA 3.3 COMMUNITY LICENSE AGREEMENT\nLlama 3.3 Version Release Date: December 6, 2024\n"Agreement" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n"Documentation" means the specifications, manuals and documentation accompanying Llama 3.3 distributed by Meta at https://www.llama.com/docs/overview.\n"Licensee" or "you" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n"Llama 3.3" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://www.llama.com/llama-downloads.\n"Llama Materials" means, collectively, Meta’s proprietary Llama 3.3 and Documentation (and any portion thereof) made available under this Agreement.\n"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\nBy clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.\n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama” at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you._\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “Llama 3.3 is licensed under the Llama 3.3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://www.llama.com/llama3\_3/use-policy), which is hereby incorporated by reference into this Agreement. \n2. Additional Commercial Terms. If, on the Llama 3.3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Llama 3.3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Llama 3.3. If you access or use Llama 3.3, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at https://www.llama.com/llama3\_3/use-policy.\nProhibited Uses\nWe want everyone to use Llama 3.3 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.3 to:\n1. Violate the law or others’ rights, including to:\n\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as: \n 1. Violence or terrorism \n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material \n 3. Human trafficking, exploitation, and sexual violence \n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials. \n 5. Sexual solicitation \n 6. Any other criminal activity\n\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n\n 5. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law\n\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n\n 8. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta\n\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.3 related to the following:\n\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997\n\n 2. Guns and illegal weapons (including weapon development)\n\n 3. Illegal drugs and regulated/controlled substances\n\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n\n3. Intentionally deceive or mislead others, including use of Llama 3.3 related to the following:\n\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n\n 3. Generating, promoting, or further distributing spam\n\n 4. Impersonating another individual without consent, authorization, or legal right\n\n 5. Representing that the use of Llama 3.3 or outputs are human-generated\n\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n\n4. Fail to appropriately disclose to end users any known dangers of your AI system\n5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.3\nWith respect to any multimodal models included in Llama 3.3, the rights granted under Section 1(a) of the Llama 3.3 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.\nPlease report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:\n* Reporting issues with the model: https://github.com/meta-llama/llama-models/issues * Reporting risky content generated by the model: developers.facebook.com/llama\_output\_feedback * Reporting bugs and security concerns: facebook.com/whitehat/info * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.3: [email protected] "
    extra_gated_fields:
    First Name: text
    Last Name: text
    Date of birth: date_picker
    Country: country
    Affiliation: text
    Job title:
    type: select
    options:
    • Student
    • Research Graduate
    • AI researcher
    • AI developer/engineer
    • Reporter
    • Other
      geo: ip_location
      By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
      extra_gated_description: >-
      The information you provide will be collected, stored, processed and shared in
      accordance with the Meta Privacy
      Policy
      .
      extra_gated_button_content: Submit
      license: llama3.3

huihui-ai/Llama-3.3-70B-Instruct-abliterated

This is an uncensored version of meta-llama/Llama-3.3-70B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

If you don't get the result you want, you can try the same question again.

Use with ollama

You can use huihui_ai/llama3.3-abliterated directly,

ollama run huihui_ai/llama3.3-abliterated

Use with transformers

Starting with transformers >= 4.43.0 onward, you can run conversational inference using the Transformers pipeline abstraction or by leveraging the Auto classes with the generate() function.

Make sure to update your transformers installation via pip install --upgrade transformers.

See the snippet below for usage with Transformers:

import transformers
import torch

model_id = "huihui-ai/Llama-3.3-70B-Instruct-abliterated"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

outputs = pipeline(
    messages,
    max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])

README history 1 version

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

  1. 2026-08-18Duplicate from huihui-ai/Llama-3.3-70B-Instruct-abliterated5c60bc616.1 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.

Open in Abliteration