Hugging Face's logo

AlioLeuchtmann
/
Qwen2.5_3B_VL_PDF_ROTATION_DETECTION_MK1

Image-Text-to-Text
Transformers
Safetensors
German
English
qwen2_5_vl
image-to-text
pdf
rotation
ocr
document
scan
conversational
text-generation-inference
Model card Files Community
AlioLeuchtmann commited on
Commit
43e2bce
·
verified ·
1 Parent(s): bf4b793

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. .ipynb_checkpoints/trainer_state-checkpoint.json +0 -0
  2. config.json +0 -1
  3. generation_config.json +13 -0
  4. model-00001-of-00002.safetensors +3 -0
  5. model-00002-of-00002.safetensors +3 -0
  6. model.safetensors.index.json +0 -0
  7. preprocessor_config.json +29 -0
  8. rng_state.pth +3 -0
  9. scheduler.pt +3 -0
  10. tokenizer_config.json +0 -4
  11. trainer_state.json +0 -0
  12. training_args.bin +3 -0
  13. video_preprocessor_config.json +86 -0
.ipynb_checkpoints/trainer_state-checkpoint.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json CHANGED
@@ -102,4 +102,3 @@
102
  "vision_token_id": 151654,
103
  "vocab_size": 151936
104
  }
105
-
 
102
  "vision_token_id": 151654,
103
  "vocab_size": 151936
104
  }
 
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 1e-06,
11
+ "transformers_version": "4.52.4",
12
+ "use_cache": false
13
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75679c913bf8bd52f0561da58561f863db6cc31fa5f7ec53aa6aa0cc19352d8c
3
+ size 4997750760
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:431fac587a95743d43aa1ff4c431e26f60c95a03619d92543514a5b79fc8b35a
3
+ size 2511587184
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1a97db8e41139aa1239ba7fb79ddeb0af5998c6305a440c1fe182e6ad02f2f5
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f133779dff09d454ed2cd308aa13a11fc42ceba9630e0c8d633ac94e69c089f
3
+ size 1064
tokenizer_config.json CHANGED
@@ -199,12 +199,8 @@
199
  "eos_token": "<|im_end|>",
200
  "errors": "replace",
201
  "extra_special_tokens": {},
202
- "max_length": null,
203
  "model_max_length": 131072,
204
- "pad_to_multiple_of": null,
205
  "pad_token": "<|endoftext|>",
206
- "pad_token_type_id": 0,
207
- "padding_side": "right",
208
  "processor_class": "Qwen2_5_VLProcessor",
209
  "split_special_tokens": false,
210
  "tokenizer_class": "Qwen2Tokenizer",
 
199
  "eos_token": "<|im_end|>",
200
  "errors": "replace",
201
  "extra_special_tokens": {},
 
202
  "model_max_length": 131072,
 
203
  "pad_token": "<|endoftext|>",
 
 
204
  "processor_class": "Qwen2_5_VLProcessor",
205
  "split_special_tokens": false,
206
  "tokenizer_class": "Qwen2Tokenizer",
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5696d29f4d9b400a03f7d208f17f9de75f947d6b4a3fc715e8c7e8a75c6ec2d7
3
+ size 5624
video_preprocessor_config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_kwargs_names": [
3
+ "do_convert_rgb",
4
+ "do_resize",
5
+ "size",
6
+ "size_divisor",
7
+ "default_to_square",
8
+ "resample",
9
+ "do_rescale",
10
+ "rescale_factor",
11
+ "do_normalize",
12
+ "image_mean",
13
+ "image_std",
14
+ "do_pad",
15
+ "do_center_crop",
16
+ "crop_size",
17
+ "data_format",
18
+ "input_data_format",
19
+ "device",
20
+ "min_pixels",
21
+ "max_pixels",
22
+ "patch_size",
23
+ "temporal_patch_size",
24
+ "merge_size"
25
+ ],
26
+ "crop_size": null,
27
+ "data_format": "channels_first",
28
+ "default_to_square": true,
29
+ "device": null,
30
+ "do_center_crop": null,
31
+ "do_convert_rgb": true,
32
+ "do_normalize": true,
33
+ "do_pad": null,
34
+ "do_rescale": true,
35
+ "do_resize": true,
36
+ "image_mean": [
37
+ 0.48145466,
38
+ 0.4578275,
39
+ 0.40821073
40
+ ],
41
+ "image_processor_type": "Qwen2VLImageProcessor",
42
+ "image_std": [
43
+ 0.26862954,
44
+ 0.26130258,
45
+ 0.27577711
46
+ ],
47
+ "input_data_format": null,
48
+ "max_pixels": 12845056,
49
+ "merge_size": 2,
50
+ "min_pixels": 3136,
51
+ "model_valid_processing_keys": [
52
+ "do_convert_rgb",
53
+ "do_resize",
54
+ "size",
55
+ "size_divisor",
56
+ "default_to_square",
57
+ "resample",
58
+ "do_rescale",
59
+ "rescale_factor",
60
+ "do_normalize",
61
+ "image_mean",
62
+ "image_std",
63
+ "do_pad",
64
+ "do_center_crop",
65
+ "crop_size",
66
+ "data_format",
67
+ "input_data_format",
68
+ "device",
69
+ "min_pixels",
70
+ "max_pixels",
71
+ "patch_size",
72
+ "temporal_patch_size",
73
+ "merge_size"
74
+ ],
75
+ "patch_size": 14,
76
+ "processor_class": "Qwen2_5_VLProcessor",
77
+ "resample": 3,
78
+ "rescale_factor": 0.00392156862745098,
79
+ "size": {
80
+ "longest_edge": 12845056,
81
+ "shortest_edge": 3136
82
+ },
83
+ "size_divisor": null,
84
+ "temporal_patch_size": 2,
85
+ "video_processor_type": "Qwen2VLVideoProcessor"
86
+ }