Instructions to use VAGOsolutions/Kraken-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VAGOsolutions/Kraken-LoRA with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("VAGOsolutions/Kraken-LoRA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -41,17 +41,12 @@ Extensible Configuration: Leverages a custom configuration setup that can be eas
|
|
| 41 |
**How to load and call Kraken-LoRA model :**
|
| 42 |
```
|
| 43 |
from transformers import AutoConfig, AutoModelForCausalLM
|
| 44 |
-
from configuration_kraken_lora import KrakenConfig
|
| 45 |
-
from modeling_kraken_lora import KrakenForCausalLM
|
| 46 |
-
|
| 47 |
-
AutoConfig.register("kraken", KrakenConfig)
|
| 48 |
-
AutoModelForCausalLM.register(KrakenConfig, KrakenForCausalLM)
|
| 49 |
|
| 50 |
device = "cuda:0" ## Setup "cuda:0" if NVIDIA, "mps" if on Mac
|
| 51 |
|
| 52 |
# Load the model and config:
|
| 53 |
config = AutoConfig.from_pretrained("./kraken_model")
|
| 54 |
-
model = AutoModelForCausalLM.from_pretrained("./kraken_model",
|
| 55 |
```
|
| 56 |
|
| 57 |
# Call the Reasoning LoRA-expert:
|
|
|
|
| 41 |
**How to load and call Kraken-LoRA model :**
|
| 42 |
```
|
| 43 |
from transformers import AutoConfig, AutoModelForCausalLM
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
|
| 45 |
device = "cuda:0" ## Setup "cuda:0" if NVIDIA, "mps" if on Mac
|
| 46 |
|
| 47 |
# Load the model and config:
|
| 48 |
config = AutoConfig.from_pretrained("./kraken_model")
|
| 49 |
+
model = AutoModelForCausalLM.from_pretrained("./kraken_model", trust_remote_code=True)
|
| 50 |
```
|
| 51 |
|
| 52 |
# Call the Reasoning LoRA-expert:
|