GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
phronetic-ai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
phronetic-ai
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Owlet-HAR-1 is a specialized vision-language model fine-tuned for human activity recognition tasks. The model processes video input and classifies human activities across 51 different action categories, ranging from facial expressions to complex body movements and object interactions.
The model is designed for direct video activity recognition tasks. It takes video input and outputs a single word describing the primary human activity being performed. The model could be used for:
The model can be integrated into larger systems for:
python
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessorfrom qwen_vl_utils import process_vision_infoimport torch # Load the model and processormodel = Qwen2VLForConditionalGeneration.from_pretrained( "phronetic-ai/owlet-har-1", torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)processor = AutoProcessor.from_pretrained("phronetic-ai/owlet-har-1", trust_remote_code=True) # Video inference - Multiple input methods supported: # Method 1: Using video frames as image listmessages = [ { "role": "user", "content": [ { "type": "video", "video": [ "file:///path/to/frame1.jpg", "file:///path/to/frame2.jpg", "file:///path/to/frame3.jpg", "file:///path/to/frame4.jpg", ], }, {"type": "text", "text": "What's the activity the person is doing in this video? Answer in one word only."}, ], }] # Method 2: Using local video filemessages = [ { "role": "user", "content": [ { "type": "video", "video": "file:///path/to/your_video.mp4", "max_pixels": 360 * 420, "fps": 1.0, }, {"type": "text", "text": "What's the activity the person is doing in this video? Answer in one word only."}, ], }] # Method 3: Using video URLmessages = [ { "role": "user", "content": [ { "type": "video", "video": "https://your-video-url.com/video.mp4", }, {"type": "text", "text": "What's the activity the person is doing in this video? Answer in one word only."}, ], }] # Preparation for inferencetext = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True)image_inputs, video_inputs, video_kwargs = process_vision_info(messages, return_video_kwargs=True)inputs = processor( text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt", **video_kwargs,)inputs = inputs.to("cuda") # Inferencegenerated_ids = model.generate(**inputs, max_new_tokens=128)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) print(f"Detected activity: {output_text[0]}")The model was fine-tuned on the HMDB51 dataset, which contains:
Evaluated on HMDB51 test split using the same 51 activity.
The model demonstrates strong performance on structured activities (gymnastics, specific movements) but struggles with activities involving rapid motion or complex object interactions. The 68.19% accuracy represents a 29.86 percentage point improvement over the base Qwen2.5-3B-VL model.
The model is trained to classify human activities in videos using a text generation objective, where the model generates a single word representing the detected activity.
If you use this model in your research, please cite:
BibTeX:
bibtex
@misc{owlet-har-1, title={Owlet-HAR-1: Human Activity Recognition Vision Language Model}, author={Phronetic AI}, year={2025}, url={https://huggingface.co/phronetic-ai/owlet-har-1}}APA: Phronetic AI. (2024). Owlet-HAR-1: Human Activity Recognition Vision Language Model. Hugging Face. https://huggingface.co/phronetic-ai/owlet-har-1
Phronetic AI Research Team
For questions about this model, please contact: divyansh.makkar@phronetic.ai
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessorfrom qwen_vl_utils import process_vision_infoimport torch # Load the model and processormodel = Qwen2VLForConditionalGeneration.from_pretrained( "phronetic-ai/owlet-har-1", torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)processor = AutoProcessor.from_pretrained("phronetic-ai/owlet-har-1", trust_remote_code=True) # Video inference - Multiple input methods supported: # Method 1: Using video frames as image listmessages = [ { "role": "user", "content": [ { "type": "video", "video": [ "file:///path/to/frame1.jpg", "file:///path/to/frame2.jpg", "file:///path/to/frame3.jpg", "file:///path/to/frame4.jpg", ], }, {"type": "text", "text": "What's the activity the person is doing in this video? Answer in one word only."}, ], }] # Method 2: Using local video filemessages = [ { "role": "user", "content": [ { "type": "video", "video": "file:///path/to/your_video.mp4", "max_pixels": 360 * 420, "fps": 1.0, }, {"type": "text", "text": "What's the activity the person is doing in this video? Answer in one word only."}, ], }] # Method 3: Using video URLmessages = [ { "role": "user", "content": [ { "type": "video", "video": "https://your-video-url.com/video.mp4", }, {"type": "text", "text": "What's the activity the person is doing in this video? Answer in one word only."}, ], }] # Preparation for inferencetext = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True)image_inputs, video_inputs, video_kwargs = process_vision_info(messages, return_video_kwargs=True)inputs = processor( text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt", **video_kwargs,)inputs = inputs.to("cuda") # Inferencegenerated_ids = model.generate(**inputs, max_new_tokens=128)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) print(f"Detected activity: {output_text[0]}")@misc{owlet-har-1, title={Owlet-HAR-1: Human Activity Recognition Vision Language Model}, author={Phronetic AI}, year={2025}, url={https://huggingface.co/phronetic-ai/owlet-har-1}}