Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -1,9 +1,3 @@
|
|
1 |
-
---
|
2 |
-
license: cc-by-nc-nd-3.0
|
3 |
-
datasets:
|
4 |
-
- trinhvg/ViDRiP_Instruct_Train
|
5 |
-
- trinhvg/ViDRiP_Instruct_Test
|
6 |
-
---
|
7 |
|
8 |
# ๐งฌ ViDRiP-LLaVA: Multimodal Diagnostic Reasoning in Pathology
|
9 |
|
@@ -28,7 +22,9 @@ Our method leverages chain-of-thought (CoT) prompting to distill the reasoning c
|
|
28 |
## ๐ Datasets
|
29 |
|
30 |
### ๐น [ViDRiP_Instruct_Train](https://huggingface.co/datasets/trinhvg/ViDRiP_Instruct_Train)
|
31 |
-
### ๐น [
|
|
|
|
|
32 |
- 4,000+ instruction-style samples
|
33 |
- Each sample includes:
|
34 |
- A pathology video clip
|
@@ -43,6 +39,8 @@ Our method leverages chain-of-thought (CoT) prompting to distill the reasoning c
|
|
43 |
- Held-out test set of diagnostic Q&A pairs
|
44 |
- Used for benchmarking reasoning performance
|
45 |
|
|
|
|
|
46 |
---
|
47 |
|
48 |
## ๐ค Models
|
@@ -102,4 +100,4 @@ You can then run evaluation using the standard lmms_eval CLI interface.
|
|
102 |
license: cc-by-nc-nd-3.0
|
103 |
|
104 |
### Citation:
|
105 |
-
Coming soon
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
|
2 |
# ๐งฌ ViDRiP-LLaVA: Multimodal Diagnostic Reasoning in Pathology
|
3 |
|
|
|
22 |
## ๐ Datasets
|
23 |
|
24 |
### ๐น [ViDRiP_Instruct_Train](https://huggingface.co/datasets/trinhvg/ViDRiP_Instruct_Train)
|
25 |
+
### ๐น [ViDRiP_Instruct_Train_Video_GoogleDrive](https://drive.google.com/drive/folders/1oxZlaJpE7PGDYt32LeoGgIzwEvWdnupY?usp=sharing)
|
26 |
+
### ๐น [ViDRiP_Instruct_Train_Video_Hugging Face](https://huggingface.co/datasets/trinhvg/ViDRiP_Instruct_Train) (There is 10 zip files)
|
27 |
+
|
28 |
- 4,000+ instruction-style samples
|
29 |
- Each sample includes:
|
30 |
- A pathology video clip
|
|
|
39 |
- Held-out test set of diagnostic Q&A pairs
|
40 |
- Used for benchmarking reasoning performance
|
41 |
|
42 |
+
|
43 |
+
|
44 |
---
|
45 |
|
46 |
## ๐ค Models
|
|
|
100 |
license: cc-by-nc-nd-3.0
|
101 |
|
102 |
### Citation:
|
103 |
+
Coming soon
|