Instructions to use ybelkada/opt-125m-debug with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ybelkada/opt-125m-debug with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ybelkada/opt-125m-debug")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("ybelkada/opt-125m-debug") model = AutoModel.from_pretrained("ybelkada/opt-125m-debug") - Notebooks
- Google Colab
- Kaggle
Change BOS token from 0 to 2 as BOS token is equal to EOS for OPT. See: https://github.com/huggingface/transformers/issues/17431
#1
by patrickvonplaten - opened
- config.json +1 -1
config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"OPTModel"
|
| 6 |
],
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
-
"bos_token_id":
|
| 9 |
"d_model": 768,
|
| 10 |
"decoder_layernorm": true,
|
| 11 |
"decoder_start_token_id": 2,
|
|
|
|
| 5 |
"OPTModel"
|
| 6 |
],
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
"d_model": 768,
|
| 10 |
"decoder_layernorm": true,
|
| 11 |
"decoder_start_token_id": 2,
|