Instructions to use QuixiAI/Kraken with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use QuixiAI/Kraken with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="QuixiAI/Kraken", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("QuixiAI/Kraken", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update kraken_model/config.json
Browse files- kraken_model/config.json +5 -0
kraken_model/config.json
CHANGED
|
@@ -2,6 +2,11 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"KrakenForCausalLM"
|
| 4 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"config_dict": {
|
| 6 |
"class_indices": {
|
| 7 |
"LABEL_0": 0,
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"KrakenForCausalLM"
|
| 4 |
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoConfig": "configuration_kraken.KrakenConfig",
|
| 7 |
+
"AutoModel": "modeling_kraken.KrakenForCausalLM",
|
| 8 |
+
"AutoModelForCausalLM": "modeling_kraken.KrakenForCausalLM"
|
| 9 |
+
},
|
| 10 |
"config_dict": {
|
| 11 |
"class_indices": {
|
| 12 |
"LABEL_0": 0,
|