Instructions to use keras/qwen3_embedding_0.6b_en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/qwen3_embedding_0.6b_en with KerasHub:
import keras_hub # Load CausalLM model (optional: use half precision for inference) causal_lm = keras_hub.models.CausalLM.from_preset("hf://keras/qwen3_embedding_0.6b_en", dtype="bfloat16") causal_lm.compile(sampler="greedy") # (optional) specify a sampler # Generate text causal_lm.generate("Keras: deep learning for", max_length=64)import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/qwen3_embedding_0.6b_en") - Keras
How to use keras/qwen3_embedding_0.6b_en with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://keras/qwen3_embedding_0.6b_en") - Notebooks
- Google Colab
- Kaggle
Download model.weights.h5 from keras/qwen3_embedding_0.6b_en: direct link, hf CLI and curl.
- Browser
- Download file 2.38 GB
-
https://huggingface.co/keras/qwen3_embedding_0.6b_en/resolve/main/model.weights.h5
- Command line
-
hf download hf://keras/qwen3_embedding_0.6b_en/model.weights.h5
-
curl -L -o model.weights.h5 https://huggingface.co/keras/qwen3_embedding_0.6b_en/resolve/main/model.weights.h5
2.38 GB
- Xet hash:
- 141b5aaadd70bded6acfd9fcff6da10e0f7fec5254f8bdd421a8c7385de7225f
- Size of remote file:
- 2.38 GB
- SHA256:
- faf25ea60a1b08fbc5e03d894c0c4c18793868f3dafd4d71c1ea4cbe1b575d2c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.