Text Generation
PEFT
Safetensors
English
llama
lora
claim-extraction
fact-checking
news
conversational
Instructions to use nidhipandya/NewsScope-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use nidhipandya/NewsScope-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/meta-llama-3.1-8b-instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "nidhipandya/NewsScope-lora") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -50,7 +50,7 @@ base = AutoModelForCausalLM.from_pretrained(
|
|
| 50 |
device_map="auto",
|
| 51 |
)
|
| 52 |
|
| 53 |
-
model = PeftModel.from_pretrained(
|
| 54 |
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
|
| 55 |
```
|
| 56 |
|
|
|
|
| 50 |
device_map="auto",
|
| 51 |
)
|
| 52 |
|
| 53 |
+
model = PeftModel.from_pretrained(base_model, "nidhipandya/NewsScope-lora")
|
| 54 |
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
|
| 55 |
```
|
| 56 |
|