Instructions to use zeromodels/moonshine_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasFormers
How to use zeromodels/moonshine_base 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
- Keras
How to use zeromodels/moonshine_base 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/moonshine_base") - Notebooks
- Google Colab
- Kaggle
Upload kf_config.json with huggingface_hub
Browse files- kf_config.json +28 -0
kf_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"library_name": "kerasformers",
|
| 3 |
+
"kerasformers_version": "1.1.3",
|
| 4 |
+
"model_module": "kerasformers.models.moonshine",
|
| 5 |
+
"model_class": "MoonshineModel",
|
| 6 |
+
"variant": "moonshine_base",
|
| 7 |
+
"weights": "model.weights.h5",
|
| 8 |
+
"model_type": "moonshine",
|
| 9 |
+
"hidden_dim": 416,
|
| 10 |
+
"encoder_num_layers": 8,
|
| 11 |
+
"decoder_num_layers": 8,
|
| 12 |
+
"encoder_attention_heads": 8,
|
| 13 |
+
"decoder_attention_heads": 8,
|
| 14 |
+
"encoder_num_kv_heads": null,
|
| 15 |
+
"decoder_num_kv_heads": null,
|
| 16 |
+
"encoder_ffn_dim": 1664,
|
| 17 |
+
"decoder_ffn_dim": 1664,
|
| 18 |
+
"vocab_size": 32768,
|
| 19 |
+
"max_position_embeddings": 194,
|
| 20 |
+
"partial_rotary_factor": 0.62,
|
| 21 |
+
"rope_theta": 10000.0,
|
| 22 |
+
"encoder_activation": "gelu",
|
| 23 |
+
"decoder_activation": "silu",
|
| 24 |
+
"layer_norm_eps": 1e-05,
|
| 25 |
+
"generate_args": {
|
| 26 |
+
"max_new_tokens": 200
|
| 27 |
+
}
|
| 28 |
+
}
|