Instructions to use deepmind/language-perceiver with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepmind/language-perceiver with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="deepmind/language-perceiver")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("deepmind/language-perceiver") model = AutoModelForMaskedLM.from_pretrained("deepmind/language-perceiver") - Notebooks
- Google Colab
- Kaggle
Update PyTorch model
Browse files- config.json +4 -0
config.json
CHANGED
|
@@ -22,6 +22,10 @@
|
|
| 22 |
"self_attention_widening_factor": 1,
|
| 23 |
"seq_len": 2048,
|
| 24 |
"torch_dtype": "float32",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
"transformers_version": "4.11.0.dev0",
|
| 26 |
"use_query_residual": true,
|
| 27 |
"v_channels": 1280,
|
|
|
|
| 22 |
"self_attention_widening_factor": 1,
|
| 23 |
"seq_len": 2048,
|
| 24 |
"torch_dtype": "float32",
|
| 25 |
+
"train_size": [
|
| 26 |
+
368,
|
| 27 |
+
496
|
| 28 |
+
],
|
| 29 |
"transformers_version": "4.11.0.dev0",
|
| 30 |
"use_query_residual": true,
|
| 31 |
"v_channels": 1280,
|