Instructions to use VAGOsolutions/Kraken-Multilingual with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VAGOsolutions/Kraken-Multilingual with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="VAGOsolutions/Kraken-Multilingual", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("VAGOsolutions/Kraken-Multilingual", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -39,18 +39,14 @@ Extensible Configuration: Leverages a custom configuration setup that can be eas
|
|
| 39 |
|
| 40 |
**How to load and call Kraken-Multilingual model :**
|
| 41 |
```
|
| 42 |
-
from transformers import
|
| 43 |
-
|
| 44 |
-
from modeling_kraken import KrakenForCausalLM
|
| 45 |
|
| 46 |
-
AutoConfig.register("kraken", KrakenConfig)
|
| 47 |
-
AutoModelForCausalLM.register(KrakenConfig, KrakenForCausalLM)
|
| 48 |
|
| 49 |
device = "cuda:0" ## Setup "cuda:0" if NVIDIA, "mps" if on Mac
|
| 50 |
|
| 51 |
# Load the model and config:
|
| 52 |
-
|
| 53 |
-
model = AutoModelForCausalLM.from_pretrained("./kraken_model", config=config, trust_remote_code=True)
|
| 54 |
```
|
| 55 |
|
| 56 |
# Call the German expert:
|
|
|
|
| 39 |
|
| 40 |
**How to load and call Kraken-Multilingual model :**
|
| 41 |
```
|
| 42 |
+
from transformers import AutoModelForCausalLM
|
| 43 |
+
|
|
|
|
| 44 |
|
|
|
|
|
|
|
| 45 |
|
| 46 |
device = "cuda:0" ## Setup "cuda:0" if NVIDIA, "mps" if on Mac
|
| 47 |
|
| 48 |
# Load the model and config:
|
| 49 |
+
model = AutoModelForCausalLM.from_pretrained("./kraken_model", trust_remote_code=True)
|
|
|
|
| 50 |
```
|
| 51 |
|
| 52 |
# Call the German expert:
|