---
library_name: vllm
language:
- en
- fr
- es
- de
- it
- pt
- nl
- zh
- ja
- ko
- ar
license: apache-2.0
inference: false
base_model:
- mistralai/Ministral-3-3B-Reasoning-2512
extra_gated_description: >-
  If you want to learn more about how we process your personal data, please read
  our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
tags:
- mistral-common
- abliterated
- uncensored
---

# huihui-ai/Huihui-Ministral-3-3B-Reasoning-2512-abliterated
This is an uncensored version of [mistralai/Ministral-3-3B-Reasoning-2512](https://huggingface.co/mistralai/Ministral-3-3B-Reasoning-2512) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).  

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

## Chat with Image

```
import torch
from transformers import Mistral3ForConditionalGeneration, MistralCommonBackend
from PIL import Image, ImageOps
import base64
import io
from datetime import datetime, timedelta
import os

model_id = "huihui-ai/Huihui-Ministral-3-3B-Reasoning-2512-abliterated"

tokenizer = MistralCommonBackend.from_pretrained(model_id, trust_remote_code=True)

model = Mistral3ForConditionalGeneration.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

model = model.cuda()

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

with Image.open(image_path) as img:
    extension_to_format = {
        ".png": "PNG",
        ".jpg": "JPEG",
        ".jpeg": "JPEG"
    }
    image_format = extension_to_format.get(
        "." + image_path.lower().split(".")[-1], "JPEG"
    )

    buffered = io.BytesIO()
    img.save(buffered, format=image_format)
    base64_string = base64.b64encode(buffered.getvalue()).decode("utf-8")
    image_url = f"data:image/{'png' if image_format == 'PNG' else 'jpeg'};base64,{base64_string}"

    messages = [
        {
            "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.apply_chat_template(
        messages,
        add_generation_prompt=True,
        return_dict=True,
        return_tensors="pt"
    ).to("cuda")

    tokenized["input_ids"] = tokenized["input_ids"].to(device="cuda")
    tokenized["pixel_values"] = tokenized["pixel_values"].to(dtype=torch.bfloat16, device="cuda")
    image_sizes = [tokenized["pixel_values"].shape[-2:]]

    output = model.generate(
        **tokenized,
        image_sizes=image_sizes,
        max_new_tokens=512,
    )[0]

    decoded_output = tokenizer.decode(output[len(tokenized["input_ids"][0]):])
    print(decoded_output)
```

### 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](https://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（BTC):
```
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
```
- Support our work on [Ko-fi](https://ko-fi.com/huihuiai)!