Instructions to use google/switch-base-64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/switch-base-64 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/switch-base-64") model = AutoModelForSeq2SeqLM.from_pretrained("google/switch-base-64") - Notebooks
- Google Colab
- Kaggle
Update config.json
#5
by ybelkada - opened
- config.json +1 -0
config.json
CHANGED
|
@@ -12,6 +12,7 @@
|
|
| 12 |
"encoder_sparse_step": 2,
|
| 13 |
"eos_token_id": 1,
|
| 14 |
"expert_capacity": 64,
|
|
|
|
| 15 |
"feed_forward_proj": "relu",
|
| 16 |
"initializer_factor": 1.0,
|
| 17 |
"is_encoder_decoder": true,
|
|
|
|
| 12 |
"encoder_sparse_step": 2,
|
| 13 |
"eos_token_id": 1,
|
| 14 |
"expert_capacity": 64,
|
| 15 |
+
"decoder_start_token_id": 0,
|
| 16 |
"feed_forward_proj": "relu",
|
| 17 |
"initializer_factor": 1.0,
|
| 18 |
"is_encoder_decoder": true,
|