Upload folder using huggingface_hub
Browse files- handle_stage3.py +9 -1
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- trainer_state.json +0 -0
- training_args.bin +1 -1
handle_stage3.py
CHANGED
@@ -10,7 +10,7 @@ audio_asr_folder = '/mnt/bn/tns-algo-video-public-my2/wangpeng.an/data'
|
|
10 |
audio_caption_folder = '/mnt/bn/tns-algo-video-public-my2/wangpeng.an/data/audio_caption'
|
11 |
video_folder = '/mnt/bn/tns-algo-video-public-my2/wangpeng.an/data/video'
|
12 |
image_folder = '/mnt/bn/tns-algo-video-public-my2/wangpeng.an/data/video/Video-LLaVA'
|
13 |
-
new_json_path = '/mnt/bn/tns-algo-video-public-my2/wangpeng.an/data/multidataset/
|
14 |
|
15 |
# Load JSON data
|
16 |
with open(data_json_path, 'r') as f:
|
@@ -103,3 +103,11 @@ print(f"Saved {len(new_items)} valid items to {new_json_path}")
|
|
103 |
print(f"Total and missing files by type:")
|
104 |
for file_type, counts in file_counts.items():
|
105 |
print(f"{file_type}: Total = {counts['total']}, Missing = {counts['missing']}")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
audio_caption_folder = '/mnt/bn/tns-algo-video-public-my2/wangpeng.an/data/audio_caption'
|
11 |
video_folder = '/mnt/bn/tns-algo-video-public-my2/wangpeng.an/data/video'
|
12 |
image_folder = '/mnt/bn/tns-algo-video-public-my2/wangpeng.an/data/video/Video-LLaVA'
|
13 |
+
new_json_path = '/mnt/bn/tns-algo-video-public-my2/wangpeng.an/data/multidataset/video_image_asr_caption_pre_1211.json'
|
14 |
|
15 |
# Load JSON data
|
16 |
with open(data_json_path, 'r') as f:
|
|
|
103 |
print(f"Total and missing files by type:")
|
104 |
for file_type, counts in file_counts.items():
|
105 |
print(f"{file_type}: Total = {counts['total']}, Missing = {counts['missing']}")
|
106 |
+
|
107 |
+
miss = {'image':[], 'video':[], 'audio_caption':[], 'audio_asr':[]}
|
108 |
+
for text in texts:
|
109 |
+
if 'image' in text:
|
110 |
+
miss['image'].append(text)
|
111 |
+
if 'video' in text:
|
112 |
+
miss['video'].append(text)
|
113 |
+
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f313f086266a38788feecf8bfe1da2ad4d636efcca76d8c33694d7d706380ac3
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9226e926895e979759395e0fca0f6ee2cde9195436102fb8bf8f1c2185c6fac7
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f3e43677d7653cb27ecbf48f279ac17e165b23fa1b00bc2df659bca6b4e2928
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3851682320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f69b0b8973f33f4ccb0997073ad546ee2e9c9aed90af6d00bbee0b0981b39d8
|
3 |
size 3851682320
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cd17e0233af3edc9aa948c15991532dc6890cde50f60d6c79801ed6637ccd56
|
3 |
size 6776
|