Instructions to use openai/jukebox-1b-lyrics with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/jukebox-1b-lyrics with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="openai/jukebox-1b-lyrics")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("openai/jukebox-1b-lyrics", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
#8
by ArthurZ HF Staff - opened
- config.json +2 -2
config.json
CHANGED
|
@@ -77,7 +77,7 @@
|
|
| 77 |
"alignment_head": null,
|
| 78 |
"alignment_layer": null,
|
| 79 |
"attention_multiplier": 0.25,
|
| 80 |
-
"attention_pattern": "
|
| 81 |
"attn_dropout": 0,
|
| 82 |
"attn_res_scale": false,
|
| 83 |
"blocks": 64,
|
|
@@ -134,7 +134,7 @@
|
|
| 134 |
"alignment_head": null,
|
| 135 |
"alignment_layer": null,
|
| 136 |
"attention_multiplier": 0.25,
|
| 137 |
-
"attention_pattern": "
|
| 138 |
"attn_dropout": 0,
|
| 139 |
"attn_res_scale": false,
|
| 140 |
"blocks": 64,
|
|
|
|
| 77 |
"alignment_head": null,
|
| 78 |
"alignment_layer": null,
|
| 79 |
"attention_multiplier": 0.25,
|
| 80 |
+
"attention_pattern": "raw_column_previous_row_attention",
|
| 81 |
"attn_dropout": 0,
|
| 82 |
"attn_res_scale": false,
|
| 83 |
"blocks": 64,
|
|
|
|
| 134 |
"alignment_head": null,
|
| 135 |
"alignment_layer": null,
|
| 136 |
"attention_multiplier": 0.25,
|
| 137 |
+
"attention_pattern": "raw_column_previous_row_attention",
|
| 138 |
"attn_dropout": 0,
|
| 139 |
"attn_res_scale": false,
|
| 140 |
"blocks": 64,
|