Upload 9 files
Browse files- .gitattributes +4 -41
- app.py +25 -1
- metadata.json +7 -1
- model_index.json +7 -0
- tokenizer_config.json +6 -0
.gitattributes
CHANGED
@@ -1,41 +1,4 @@
|
|
1 |
-
*.
|
2 |
-
*.
|
3 |
-
*.
|
4 |
-
*.
|
5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
-
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
-
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
-
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
-
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
-
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
-
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
-
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
-
models/TabRec/TableMaster/ch_PP-OCRv3_det_infer/inference.pdiparams filter=lfs diff=lfs merge=lfs -text
|
37 |
-
models/TabRec/TableMaster/ch_PP-OCRv3_det_infer/inference.pdmodel filter=lfs diff=lfs merge=lfs -text
|
38 |
-
models/TabRec/TableMaster/ch_PP-OCRv3_rec_infer/inference.pdiparams filter=lfs diff=lfs merge=lfs -text
|
39 |
-
models/TabRec/TableMaster/ch_PP-OCRv3_rec_infer/inference.pdmodel filter=lfs diff=lfs merge=lfs -text
|
40 |
-
models/TabRec/TableMaster/table_structure_tablemaster_infer/inference.pdiparams filter=lfs diff=lfs merge=lfs -text
|
41 |
-
models/TabRec/TableMaster/table_structure_tablemaster_infer/inference.pdmodel filter=lfs diff=lfs merge=lfs -text
|
|
|
1 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
app.py
CHANGED
@@ -1 +1,25 @@
|
|
1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import PreTrainedModel
|
2 |
+
from typing import Optional
|
3 |
+
import torch
|
4 |
+
|
5 |
+
class MinerUModel(PreTrainedModel):
|
6 |
+
def __init__(self, config):
|
7 |
+
super().__init__(config)
|
8 |
+
self.config = config
|
9 |
+
|
10 |
+
@staticmethod
|
11 |
+
def load_model():
|
12 |
+
from model_loader import MinerUModelLoader
|
13 |
+
return MinerUModelLoader.load_models("./")
|
14 |
+
|
15 |
+
def forward(self, input_data):
|
16 |
+
# 实现前向传播逻辑
|
17 |
+
pass
|
18 |
+
|
19 |
+
def load_model():
|
20 |
+
model = MinerUModel.from_pretrained("./")
|
21 |
+
return model
|
22 |
+
|
23 |
+
def inference(pdf_content):
|
24 |
+
model = load_model()
|
25 |
+
return model(pdf_content)
|
metadata.json
CHANGED
@@ -2,5 +2,11 @@
|
|
2 |
"language": ["zh", "en"],
|
3 |
"license": "apache-2.0",
|
4 |
"tags": ["document-conversion", "pdf-to-markdown"],
|
5 |
-
"pipeline_tag": "document-conversion"
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
|
|
2 |
"language": ["zh", "en"],
|
3 |
"license": "apache-2.0",
|
4 |
"tags": ["document-conversion", "pdf-to-markdown"],
|
5 |
+
"pipeline_tag": "document-conversion",
|
6 |
+
"library_name": "transformers",
|
7 |
+
"task_specific_params": {
|
8 |
+
"pdf-to-markdown": {
|
9 |
+
"max_length": 1024
|
10 |
+
}
|
11 |
+
}
|
12 |
}
|
model_index.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "kitjesen/MinerU",
|
3 |
+
"architectures": ["MinerUModel"],
|
4 |
+
"model_type": "mineru",
|
5 |
+
"transformers_version": "4.28.0",
|
6 |
+
"framework": "pytorch"
|
7 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_type": "mineru",
|
3 |
+
"pad_token": "[PAD]",
|
4 |
+
"unk_token": "[UNK]",
|
5 |
+
"do_lower_case": false
|
6 |
+
}
|