MetaCLIP 2
Collection
Pure-Keras 3 MetaCLIP 2 weights for kerasformers. • 16 items • Updated
How to use kerasformers/metaclip2_mt5_worldwide_m16_224 with KerasFormers:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
How to use kerasformers/metaclip2_mt5_worldwide_m16_224 with Keras:
# Available backend options are: "jax", "torch", "tensorflow".
import os
os.environ["KERAS_BACKEND"] = "jax"
import keras
model = keras.saving.load_model("hf://kerasformers/metaclip2_mt5_worldwide_m16_224")
Pure-Keras 3 weights for kerasformers, mirrored from the GitHub release. License: cc-by-nc-4.0.
from kerasformers.models.metaclip2 import MetaClip2Model, MetaClip2Mt5Tokenizer
model = MetaClip2Model.from_weights("metaclip2_mt5_worldwide_m16_224")
tokenizer = MetaClip2Mt5Tokenizer()