Update README.md
Browse files
README.md
CHANGED
|
@@ -54,4 +54,21 @@ You are given the following text. Please provide a summary in 5-10 key points, d
|
|
| 54 |
### Original Text:
|
| 55 |
{}
|
| 56 |
|
| 57 |
-
### Key Points Summary (in bullet points):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
### Original Text:
|
| 55 |
{}
|
| 56 |
|
| 57 |
+
### Key Points Summary (in bullet points):
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
# Model Loading Instructions
|
| 62 |
+
|
| 63 |
+
To load this model, use the following code snippet:
|
| 64 |
+
|
| 65 |
+
```python
|
| 66 |
+
from peft import AutoPeftModelForCausalLM
|
| 67 |
+
from transformers import AutoTokenizer
|
| 68 |
+
|
| 69 |
+
# Replace "lora_model" with your actual model name
|
| 70 |
+
model = AutoPeftModelForCausalLM.from_pretrained(
|
| 71 |
+
"saishshinde15/Summmary_Model_Llama-3.2-1B-Instruct", # YOUR MODEL YOU USED FOR TRAINING
|
| 72 |
+
load_in_4bit=True, # Adjust as needed
|
| 73 |
+
)
|
| 74 |
+
tokenizer = AutoTokenizer.from_pretrained("saishshinde15/Summmary_Model_Llama-3.2-1B-Instruct")
|