Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,48 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: meta-llama/Llama-2-7b-hf
|
4 |
+
license: apache-2.0
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
---
|
8 |
+
## Training:
|
9 |
+
|
10 |
+
Check out our githbub: https://github.com/HIRC-SNUBH/Curation_LLM_PathoReport.git
|
11 |
+
|
12 |
+
## Inference
|
13 |
+
``` python
|
14 |
+
from datasets import load_dataset
|
15 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
16 |
+
from peft import PeftModel
|
17 |
+
|
18 |
+
|
19 |
+
base_model = AutoModelForCausalLM.from_pretrained(
|
20 |
+
'meta-llama/Llama-2-7b-chat-hf',
|
21 |
+
trust_remote_code=True,
|
22 |
+
device_map="auto",
|
23 |
+
torch_dtype=torch.float16, # optional if you have enough VRAM
|
24 |
+
)
|
25 |
+
tokenizer = AutoTokenizer.from_pretrained('meta-llama/Llama-2-7b-hf')
|
26 |
+
|
27 |
+
model = PeftModel.from_pretrained(base_model, 'Lowenzahn/PathoIE-Llama-2-7B')
|
28 |
+
model = model.eval()
|
29 |
+
```
|
30 |
+
|
31 |
+
- PEFT 0.5.0
|
32 |
+
|
33 |
+
|
34 |
+
## Citation
|
35 |
+
```
|
36 |
+
@article{cho2024ie,
|
37 |
+
title={Extracting lung cancer staging descriptors from pathology reports: a generative language model approach},
|
38 |
+
author={Hyeongmin Cho and Sooyoung Yoo and Borham Kim and Sowon Jang and Leonard Sunwoo and Sanghwan Kim and Donghyoung Lee and Seok Kim and Sejin Nam and Jin-Haeng Chung},
|
39 |
+
journal={},
|
40 |
+
volume={},
|
41 |
+
pages={},
|
42 |
+
year={},
|
43 |
+
publisher={},
|
44 |
+
issn={},
|
45 |
+
doi={},
|
46 |
+
url={}
|
47 |
+
}
|
48 |
+
```
|