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

nicoboss/Huihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated-llamacppfixed

nicoboss Mistral 24B multimodal
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/nicoboss%2FHuihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated-llamacppfixed"
Response includes
  • classification m1
  • files 25
  • benchmarks 11 entries
  • hub_downloads_all_time 1,499
  • providers 1
  • author_summary 75 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
1K
81 last 30d - cooling
Likes
1
Descendants
3
in 3 direct forks
Model age
15mo ago
created 2025-07-07
Available via
1 provider
featherless-ai
Downloads over time
Now1.5K→from28↑5,389%
05631.1K1.7K28 on Jul 9, 20251.5K on Oct 11Jul '25Sep '25Nov '25JanMarMayJulSep
Jul 9, 2025 → Oct 11 · 105 snapshots · spans 459 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
Entertainment 2.1 UGI
Hazardous 3.5 UGI
Natural Intelligence 23.93 UGI
Political lean -10.1% UGI
Sensitive-Info 28.15 UGI
SocPol 3.2 UGI
UGI 40.43 UGI
Willingness (10) 6.5 UGI
W10-Adherence 8 UGI
W10-Direct 5 UGI
Writing 36.26 UGI

Genealogy 3 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.

Metadata

License
apache-2.0
Languages
en fr de es pt it ja ko ru zh ar fa id ms ne pl ro sr sv tr uk vi hi bn
Tags
vllm safetensors mistral3 abliterated uncensored image-text-to-text conversational en fr de es pt

Related

Total size
44.7 GB
Files
25
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-07-07 15:16

Files by quantization

Auxiliary files 25 files 44.8 GB
model-00006-of-00010.safetensors 4.55 GB 60d3d05c download
model-00009-of-00010.safetensors 4.55 GB a093fe44 download
model-00003-of-00010.safetensors 4.55 GB 22f806b8 download
model-00001-of-00010.safetensors 4.55 GB b6c0aee6 download
model-00004-of-00010.safetensors 4.45 GB 10a28fc8 download
model-00007-of-00010.safetensors 4.45 GB ecc86e75 download
model-00005-of-00010.safetensors 4.45 GB 162992b3 download
model-00008-of-00010.safetensors 4.45 GB 96476a3e download
model-00002-of-00010.safetensors 4.45 GB c6314806 download
model-00010-of-00010.safetensors 4.26 GB 101361dc download
tekken.json 18.5 MB 6e250168 download
tokenizer.json 16.3 MB b76085f9 download
tokenizer_config.json 193 KB c61ab81d download
model.safetensors.index.json 57.2 KB ff69e24f download
special_tokens_map.json 20.9 KB a47054b4 download
chat_template.jinja 14.4 KB 7e8f4ae7 download
README.md 7.05 KB 0bceed82 download
chat_template.json 2.71 KB d55f5350 download
SYSTEM_PROMPT.txt 2.33 KB 6945458c download
.gitattributes 1.58 KB 0d4cb185 download
config.json 1.32 KB 6b45cd22 download
params.json 768 B 94420c6d download
preprocessor_config.json 634 B e6fae040 download
processor_config.json 189 B 0092b0f4 download
generation_config.json 180 B 038c98e7 download

README current version from Hugging Face


language:

  • en
  • fr
  • de
  • es
  • pt
  • it
  • ja
  • ko
  • ru
  • zh
  • ar
  • fa
  • id
  • ms
  • ne
  • pl
  • ro
  • sr
  • sv
  • tr
  • uk
  • vi
  • hi
  • bn
    license: apache-2.0
    library_name: vllm
    inference: false
    base_model:
  • mistralai/Mistral-Small-3.2-24B-Instruct-2506
    extra_gated_description: >-
    If you want to learn more about how we process your personal data, please read
    our Privacy Policy.
    pipeline_tag: image-text-to-text
    tags:
  • abliterated
  • uncensored

huihui-ai/Huihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated

This is an uncensored version of mistralai/Mistral-Small-3.2-24B-Instruct-2506 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.

It was only the text part that was processed, not the image part.

Usage

from datetime import datetime, timedelta
import torch

from mistral_common.protocol.instruct.request import ChatCompletionRequest
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from huggingface_hub import hf_hub_download
from transformers import Mistral3ForConditionalGeneration


def load_system_prompt(repo_id: str, filename: str) -> str:
    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
    with open(file_path, "r") as file:
        system_prompt = file.read()
    today = datetime.today().strftime("%Y-%m-%d")
    yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
    model_name = repo_id.split("/")[-1]
    return system_prompt.format(name=model_name, today=today, yesterday=yesterday)


model_id = "huihui-ai/Huihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated"
SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")

tokenizer = MistralTokenizer.from_hf_hub(model_id)

model = Mistral3ForConditionalGeneration.from_pretrained(
    model_id, torch_dtype=torch.bfloat16
)

image_url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438"

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.",
            },
            {"type": "image_url", "image_url": {"url": image_url}},
        ],
    },
]

tokenized = tokenizer.encode_chat_completion(ChatCompletionRequest(messages=messages))

input_ids = torch.tensor([tokenized.tokens])
attention_mask = torch.ones_like(input_ids)
pixel_values = torch.tensor(tokenized.images[0], dtype=torch.bfloat16).unsqueeze(0)
image_sizes = torch.tensor([pixel_values.shape[-2:]])

output = model.generate(
    input_ids=input_ids,
    attention_mask=attention_mask,
    pixel_values=pixel_values,
    image_sizes=image_sizes,
    max_new_tokens=1000,
)[0]

decoded_output = tokenizer.decode(output[len(tokenized.tokens) :])
print(decoded_output)
# In this situation, you are playing a Pokémon game where your Pikachu (Level 42) is facing a wild Pidgey (Level 17). Here are the possible actions you can take and an analysis of each:

# 1. **FIGHT**:
#    - **Pros**: Pikachu is significantly higher level than the wild Pidgey, which suggests that it should be able to defeat Pidgey easily. This could be a good opportunity to gain experience points and possibly items or money.
#    - **Cons**: There is always a small risk of Pikachu fainting, especially if Pidgey has a powerful move or a status effect that could hinder Pikachu. However, given the large level difference, this risk is minimal.

# 2. **BAG**:
#    - **Pros**: You might have items in your bag that could help in this battle, such as Potions, Poké Balls, or Berries. Using an item could help you capture Pidgey or heal Pikachu if needed.
#    - **Cons**: Using items might not be necessary given the level difference. It could be more efficient to just fight and defeat Pidgey quickly.

# 3. **POKÉMON**:
#    - **Pros**: You might have another Pokémon in your party that is better suited for this battle or that you want to gain experience. Switching Pokémon could also be strategic if you want to train a lower-level Pokémon.
#    - **Cons**: Switching Pokémon might not be necessary since Pikachu is at a significant advantage. It could also waste time and potentially give Pidgey a turn to attack.

# 4. **RUN**:
#    - **Pros**: Running away could be a quick way to avoid the battle altogether. This might be useful if you are trying to conserve resources or if you are in a hurry to get to another location.
#    - **Cons**: Running away means you miss out on the experience points, items, or money that you could gain from defeating Pidgey. It also might not be the most efficient use of your time if you are trying to train your Pokémon.

# ### Recommendation:
# Given the significant level advantage, the best action to take is likely **FIGHT**. This will allow you to quickly defeat Pidgey and gain experience points for Pikachu. If you are concerned about Pikachu's health, you could use the **BAG** to heal Pikachu before or during the battle. Running away or switching Pokémon does not seem necessary in this situation.

Usage Warnings

  • Risk of Sensitive or Controversial Outputs: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.

  • Not Suitable for All Audiences: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.

  • Legal and Ethical Responsibilities: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.

  • Research and Experimental Use: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.

  • Monitoring and Review Recommendations: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.

  • No Default Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.

Donation

If you like it, please click 'like' and follow us for more updates.
You can follow x.com/support_huihui to get the latest model information from huihui.ai.

Your donation helps us continue our further development and improvement, a cup of coffee can do it.
  • bitcoin:
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge

README history 1 version

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

  1. 2025-07-07Duplicate from huihui-ai/Huihui-Mistral-Small-3.2-24B-Instruct-2506-abliteratedbd3dfde7.1 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