Instructions to use arnavgrg/codealpaca-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use arnavgrg/codealpaca-qlora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf") model = PeftModel.from_pretrained(base_model, "arnavgrg/codealpaca-qlora") - Notebooks
- Google Colab
- Kaggle
Add load_in_4bit flag for base model
Browse files
README.md
CHANGED
|
@@ -44,7 +44,7 @@ To use these weights:
|
|
| 44 |
from peft import PeftModel, PeftConfig
|
| 45 |
from transformers import AutoModelForCausalLM
|
| 46 |
|
| 47 |
-
config = PeftConfig.from_pretrained("arnavgrg/codealpaca-qlora")
|
| 48 |
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
|
| 49 |
model = PeftModel.from_pretrained(model, "arnavgrg/codealpaca-qlora")
|
| 50 |
```
|
|
|
|
| 44 |
from peft import PeftModel, PeftConfig
|
| 45 |
from transformers import AutoModelForCausalLM
|
| 46 |
|
| 47 |
+
config = PeftConfig.from_pretrained("arnavgrg/codealpaca-qlora", load_in_4bit=True)
|
| 48 |
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
|
| 49 |
model = PeftModel.from_pretrained(model, "arnavgrg/codealpaca-qlora")
|
| 50 |
```
|