Instructions to use ohgnues/FiDT5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ohgnues/FiDT5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ohgnues/FiDT5", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("ohgnues/FiDT5", trust_remote_code=True) model = AutoModel.from_pretrained("ohgnues/FiDT5", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +5 -2
config.json
CHANGED
|
@@ -1,8 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "google-t5/t5-small",
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"classifier_dropout": 0.0,
|
| 7 |
"d_ff": 2048,
|
| 8 |
"d_kv": 64,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
+
"FiDForConditionalGeneration"
|
| 4 |
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoConfig": "configuration_fid.FiDConfig",
|
| 7 |
+
"AutoModel": "modeling_fid.FiDForConditionalGeneration"
|
| 8 |
+
},
|
| 9 |
"classifier_dropout": 0.0,
|
| 10 |
"d_ff": 2048,
|
| 11 |
"d_kv": 64,
|