Instructions to use zeromodels/bart_large_cnn with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/bart_large_cnn with ZeroModels:
# pip install -U zeromodels # ZeroModels is pure Keras 3, so pick a backend: "jax", "torch" or "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" from zeromodels import AutoZModel # AutoZModel reads the repo's model_type and loads the matching class. # For a task head use the matching loader, e.g. AutoZMImageClassify / AutoZMDetect / # AutoZMSemanticSegment / AutoZMTextGenerate (see zeromodels.auto). model = AutoZModel.from_weights("zeromodels/bart_large_cnn") - Keras
How to use zeromodels/bart_large_cnn with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://zeromodels/bart_large_cnn") - Notebooks
- Google Colab
- Kaggle
| { | |
| "library_name": "zeromodels", | |
| "zeromodels_version": "1.3.0", | |
| "model_module": "zeromodels.models.bart", | |
| "model_class": "BartConditionalGenerate", | |
| "variant": "bart_large_cnn", | |
| "weights": "model.weights.h5", | |
| "schema_version": 2, | |
| "model_type": "bart", | |
| "text_config": { | |
| "vocab_size": 50264, | |
| "hidden_dim": 1024, | |
| "encoder_num_layers": 12, | |
| "decoder_num_layers": 12, | |
| "encoder_attention_heads": 16, | |
| "decoder_attention_heads": 16, | |
| "encoder_ffn_dim": 4096, | |
| "decoder_ffn_dim": 4096, | |
| "max_position_embeddings": 1024, | |
| "activation_function": "gelu", | |
| "scale_embedding": false, | |
| "layer_norm_eps": 1e-05, | |
| "classifier_dropout": 0.0, | |
| "num_labels": 3, | |
| "pad_token_id": 1, | |
| "bos_token_id": 0, | |
| "eos_token_id": 2, | |
| "decoder_start_token_id": 2 | |
| }, | |
| "generate_args": { | |
| "max_new_tokens": 142 | |
| } | |
| } |