Instructions to use PhatcatDK/t5gemma-9b-2b-ul2-encoder-only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PhatcatDK/t5gemma-9b-2b-ul2-encoder-only with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="PhatcatDK/t5gemma-9b-2b-ul2-encoder-only")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("PhatcatDK/t5gemma-9b-2b-ul2-encoder-only") model = AutoModel.from_pretrained("PhatcatDK/t5gemma-9b-2b-ul2-encoder-only") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -32,7 +32,7 @@ from transformers import T5GemmaEncoderModel
|
|
| 32 |
model_path = "PhatcatDK/t5gemma-9b-2b-ul2-encoder-only"
|
| 33 |
|
| 34 |
# Load the weights
|
| 35 |
-
model =
|
| 36 |
model_path,
|
| 37 |
torch_dtype="auto", # Recommended: bfloat16
|
| 38 |
is_encoder_decoder=False, # CRITICAL: Tells Transformers there is no decoder
|
|
|
|
| 32 |
model_path = "PhatcatDK/t5gemma-9b-2b-ul2-encoder-only"
|
| 33 |
|
| 34 |
# Load the weights
|
| 35 |
+
model = T5GemmaEncoderModel.from_pretrained(
|
| 36 |
model_path,
|
| 37 |
torch_dtype="auto", # Recommended: bfloat16
|
| 38 |
is_encoder_decoder=False, # CRITICAL: Tells Transformers there is no decoder
|