Instructions to use bezzam/xcodec2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bezzam/xcodec2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="bezzam/xcodec2")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bezzam/xcodec2", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload model
Browse files- config.json +12 -12
config.json
CHANGED
|
@@ -22,6 +22,17 @@
|
|
| 22 |
"num_attention_heads": 16,
|
| 23 |
"num_hidden_layers": 12,
|
| 24 |
"num_key_value_heads": 16,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
"resnet_dropout": 0.1,
|
| 26 |
"rms_norm_eps": 1e-06,
|
| 27 |
"rope_parameters": {
|
|
@@ -112,16 +123,5 @@
|
|
| 112 |
"xvector_output_dim": 512
|
| 113 |
},
|
| 114 |
"semantic_model_id": "facebook/w2v-bert-2.0",
|
| 115 |
-
"transformers_version": "5.3.0.dev0"
|
| 116 |
-
"vq_dim": 2048,
|
| 117 |
-
"vq_levels": [
|
| 118 |
-
4,
|
| 119 |
-
4,
|
| 120 |
-
4,
|
| 121 |
-
4,
|
| 122 |
-
4,
|
| 123 |
-
4,
|
| 124 |
-
4,
|
| 125 |
-
4
|
| 126 |
-
]
|
| 127 |
}
|
|
|
|
| 22 |
"num_attention_heads": 16,
|
| 23 |
"num_hidden_layers": 12,
|
| 24 |
"num_key_value_heads": 16,
|
| 25 |
+
"quantization_dim": 2048,
|
| 26 |
+
"quantization_levels": [
|
| 27 |
+
4,
|
| 28 |
+
4,
|
| 29 |
+
4,
|
| 30 |
+
4,
|
| 31 |
+
4,
|
| 32 |
+
4,
|
| 33 |
+
4,
|
| 34 |
+
4
|
| 35 |
+
],
|
| 36 |
"resnet_dropout": 0.1,
|
| 37 |
"rms_norm_eps": 1e-06,
|
| 38 |
"rope_parameters": {
|
|
|
|
| 123 |
"xvector_output_dim": 512
|
| 124 |
},
|
| 125 |
"semantic_model_id": "facebook/w2v-bert-2.0",
|
| 126 |
+
"transformers_version": "5.3.0.dev0"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 127 |
}
|