How to use iyttor/VidVec-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="iyttor/VidVec-7B", trust_remote_code=True)
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("iyttor/VidVec-7B", trust_remote_code=True, device_map="auto")
21e271e
1
2
3
4
5
6
7
8
9
10
11
{ "fps": 2, "image_merge_size": 1, "max_frames": 180, "processor_class": "Videollama3Qwen2Processor", "video_merge_size": 2, "auto_map": { "AutoProcessor": "processing_videollama3.Videollama3Qwen2Processor" } }
