GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
huihui-ai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
huihui-ai
Model Tree
Qwen/Qwen2.5-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
You can use huihui_ai/qwen2.5-vl-abliterated:7b directly,
text
ollama run huihui_ai/qwen2.5-vl-abliterated:7bYou can use this model in your applications by loading it with Hugging Face's transformers library:
python
from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessorfrom 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)text
bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70gefrom transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessorfrom 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)