huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated

This is an uncensored version of Qwen/Qwen2.5-VL-7B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it).

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

ollama

You can use huihui_ai/qwen2.5-vl-abliterated:7b directly,

ollama run huihui_ai/qwen2.5-vl-abliterated:7b

Usage

You can use this model in your applications by loading it with Hugging Face's transformers library:

from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
 "huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated", torch_dtype="auto", device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
 {
 "role": "user",
 "content": [
 {
 "type": "image",
 "image": f"file://{image_path}",
 },
 {"type": "text", "text": "Describe this image."},
 ],
 }
]

text = processor.apply_chat_template(
 messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
 text=[text],
 images=image_inputs,
 videos=video_inputs,
 padding=True,
 return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
 out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
 generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Donation

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

• bitcoin:

 bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge

Base model

Qwen/Qwen2.5-VL-7B-Instruct

(1106)

3 items • Updated Apr 1, 2025 • 4