README.md

---
license: mit
language:
- en
- zh
base_model:
- THUDM/GLM-4.1V-9B-Thinking
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- reasoning
- abliterated
- uncensored
---

# huihui-ai/Huihui-GLM-4.1V-9B-Thinking-abliterated

This is an uncensored version of [THUDM/GLM-4.1V-9B-Thinking](https://huggingface.co/THUDM/GLM-4.1V-9B-Thinking) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/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
You can use this model in your applications by loading it with Hugging Face's `transformers` library:

```python

from transformers import AutoProcessor, Glm4vForConditionalGeneration, BitsAndBytesConfig
from PIL import Image
import requests
import torch
import base64

model_id = "huihui-ai/Huihui-GLM-4.1V-9B-Thinking-abliterated"

quant_config_4 = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_use_double_quant=True,
    llm_int8_enable_fp32_cpu_offload=True,
)

model = Glm4vForConditionalGeneration.from_pretrained(
    model_id, 
    device_map="auto", 
    quantization_config=quant_config_4,
    torch_dtype=torch.bfloat16
).eval()

processor = AutoProcessor.from_pretrained(model_id, use_fast=True)

# https://upload.wikimedia.org/wikipedia/commons/f/fa/Grayscale_8bits_palette_sample_image.png
image_path = model_id + "/Grayscale_8bits_palette_sample_image.png"

with Image.open(image_path) as image:
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": image},
                {"type": "text", "text": "Describe this image in detail."}
            ]
        }
    ]

    inputs = processor.apply_chat_template(
        messages,
        tokenize=True,
        add_generation_prompt=True,
        return_dict=True,
        return_tensors="pt"
    ).to(model.device)

    with torch.inference_mode():
        generated_ids  = model.generate(**inputs, max_new_tokens=8192)

        output_text = processor.decode(generated_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False)
        print(output_text)

```

### 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
```