Instructions to use keras/harrier_embedding_oss_270m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/harrier_embedding_oss_270m with KerasHub:
import keras_hub # Load CausalLM model (optional: use half precision for inference) causal_lm = keras_hub.models.CausalLM.from_preset("hf://keras/harrier_embedding_oss_270m", 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 TextEmbedder model task = keras_hub.models.TextEmbedder.from_preset("hf://keras/harrier_embedding_oss_270m")import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/harrier_embedding_oss_270m") - Keras
How to use keras/harrier_embedding_oss_270m with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://keras/harrier_embedding_oss_270m") - Notebooks
- Google Colab
- Kaggle
| { | |
| "module": "keras_hub.src.models.gemma3.gemma3_text_embedder", | |
| "class_name": "Gemma3TextEmbedder", | |
| "config": { | |
| "backbone": { | |
| "module": "keras_hub.src.models.gemma3.gemma3_backbone", | |
| "class_name": "Gemma3Backbone", | |
| "config": { | |
| "name": "gemma3_backbone", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "vocabulary_size": 262144, | |
| "image_size": null, | |
| "num_layers": 18, | |
| "num_query_heads": 4, | |
| "num_key_value_heads": 1, | |
| "hidden_dim": 640, | |
| "intermediate_dim": 2048, | |
| "head_dim": 256, | |
| "query_head_dim_normalize": true, | |
| "use_query_key_norm": true, | |
| "use_post_ffw_norm": true, | |
| "use_post_attention_norm": true, | |
| "attention_logit_soft_cap": null, | |
| "final_logit_soft_cap": null, | |
| "use_sliding_window_attention": false, | |
| "sliding_window_size": 512, | |
| "local_rope_scaling_factor": 1.0, | |
| "global_rope_scaling_factor": 1.0, | |
| "vision_encoder": null, | |
| "use_bidirectional_attention": false, | |
| "layer_norm_epsilon": 1e-06, | |
| "dropout": 0, | |
| "is_embedding_model": false, | |
| "pooling_intermediate_dim": null, | |
| "embedding_dim": null | |
| }, | |
| "registered_name": "keras_hub>Gemma3Backbone" | |
| }, | |
| "preprocessor": { | |
| "module": "keras_hub.src.models.gemma3.gemma3_text_embedder_preprocessor", | |
| "class_name": "Gemma3TextEmbedderPreprocessor", | |
| "config": { | |
| "name": "gemma3_text_embedder_preprocessor", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "tokenizer": { | |
| "module": "keras_hub.src.models.gemma3.gemma3_tokenizer", | |
| "class_name": "Gemma3Tokenizer", | |
| "config": { | |
| "name": "gemma3_tokenizer", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "int32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "config_file": "tokenizer.json", | |
| "proto": null, | |
| "sequence_length": null, | |
| "add_bos": false, | |
| "add_eos": false, | |
| "has_vision_tokens": true | |
| }, | |
| "registered_name": "keras_hub>Gemma3Tokenizer" | |
| }, | |
| "config_file": "preprocessor.json", | |
| "sequence_length": 256, | |
| "truncate": "round_robin" | |
| }, | |
| "registered_name": "keras_hub>Gemma3TextEmbedderPreprocessor" | |
| }, | |
| "name": "gemma3_text_embedder", | |
| "pooling_mode": "last", | |
| "normalize": true | |
| }, | |
| "registered_name": "keras_hub>Gemma3TextEmbedder" | |
| } |