WeiChow/WEAVE
Viewer β’ Updated β’ 101k β’ 2.9k β’ 12
How to use WeiChow/Bagel-weave with Transformers:
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("WeiChow/Bagel-weave", device_map="auto")Configuration Parsing Warning:Invalid JSON for config file config.json
π This is the official Bagel implementation of Weave: A Benchmark for Evaluating Multimodal Editing Models
Bagel-weave is finetuned by WEAVE-100k.
BAGEL-weave is licensed under the Apache 2.0 license. It is finetuned from Bagel-7B-MOT, Qwen2.5-7B-Instruct and siglip-so400m-14-384-flash-attn2 model, and uses the FLUX.1-schnell VAE model, all under Apache 2.0.