Update after integration (#17)
Browse files- update after integration (b9b6785fb4884bc79302d2710585c99675639794)
- update after integration (6d11b0db7c3041a2e01f09fb965e648f9df83b16)
- config.json +3 -3
- md.py +2 -2
- ocr.py +2 -2
- special_tokens_map.json +33 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
config.json
CHANGED
@@ -82,8 +82,8 @@
|
|
82 |
"bos_token_id": null,
|
83 |
"chunk_size_feed_forward": 0,
|
84 |
"cross_attention_hidden_size": null,
|
85 |
-
"
|
86 |
-
"
|
87 |
"decoder_start_token_id": null,
|
88 |
"dense_act_fn": "gelu_new",
|
89 |
"diversity_penalty": 0.0,
|
@@ -133,7 +133,7 @@
|
|
133 |
"return_dict": true,
|
134 |
"return_dict_in_generate": false,
|
135 |
"sep_token_id": null,
|
136 |
-
"
|
137 |
"suppress_tokens": null,
|
138 |
"task_specific_params": null,
|
139 |
"temperature": 1.0,
|
|
|
82 |
"bos_token_id": null,
|
83 |
"chunk_size_feed_forward": 0,
|
84 |
"cross_attention_hidden_size": null,
|
85 |
+
"intermediate_size": 3968,
|
86 |
+
"head_dim": 64,
|
87 |
"decoder_start_token_id": null,
|
88 |
"dense_act_fn": "gelu_new",
|
89 |
"diversity_penalty": 0.0,
|
|
|
133 |
"return_dict": true,
|
134 |
"return_dict_in_generate": false,
|
135 |
"sep_token_id": null,
|
136 |
+
"max_num_patches": 4096,
|
137 |
"suppress_tokens": null,
|
138 |
"task_specific_params": null,
|
139 |
"temperature": 1.0,
|
md.py
CHANGED
@@ -11,7 +11,7 @@ model = Kosmos2_5ForConditionalGeneration.from_pretrained(repo, device_map=devic
|
|
11 |
processor = AutoProcessor.from_pretrained(repo)
|
12 |
|
13 |
# sample image
|
14 |
-
url = "https://huggingface.co/microsoft/kosmos-2.5/
|
15 |
image = Image.open(requests.get(url, stream=True).raw)
|
16 |
|
17 |
prompt = "<md>"
|
@@ -30,4 +30,4 @@ generated_ids = model.generate(
|
|
30 |
)
|
31 |
|
32 |
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
|
33 |
-
print(generated_text[0])
|
|
|
11 |
processor = AutoProcessor.from_pretrained(repo)
|
12 |
|
13 |
# sample image
|
14 |
+
url = "https://huggingface.co/microsoft/kosmos-2.5/resolve/main/receipt_00008.png"
|
15 |
image = Image.open(requests.get(url, stream=True).raw)
|
16 |
|
17 |
prompt = "<md>"
|
|
|
30 |
)
|
31 |
|
32 |
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
|
33 |
+
print(generated_text[0])
|
ocr.py
CHANGED
@@ -11,7 +11,7 @@ model = Kosmos2_5ForConditionalGeneration.from_pretrained(repo, device_map=devic
|
|
11 |
processor = AutoProcessor.from_pretrained(repo)
|
12 |
|
13 |
# sample image
|
14 |
-
url = "https://huggingface.co/microsoft/kosmos-2.5/
|
15 |
image = Image.open(requests.get(url, stream=True).raw)
|
16 |
|
17 |
# bs = 1
|
@@ -70,4 +70,4 @@ for line in lines:
|
|
70 |
continue
|
71 |
line = list(map(int, line[:8]))
|
72 |
draw.polygon(line, outline="red")
|
73 |
-
image.save("output.png")
|
|
|
11 |
processor = AutoProcessor.from_pretrained(repo)
|
12 |
|
13 |
# sample image
|
14 |
+
url = "https://huggingface.co/microsoft/kosmos-2.5/resolve/main/receipt_00008.png"
|
15 |
image = Image.open(requests.get(url, stream=True).raw)
|
16 |
|
17 |
# bs = 1
|
|
|
70 |
continue
|
71 |
line = list(map(int, line[:8]))
|
72 |
draw.polygon(line, outline="red")
|
73 |
+
image.save("output.png")
|
special_tokens_map.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"boi_token": "<image>",
|
3 |
+
"bos_token": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
"eoi_token": "</image>",
|
11 |
+
"eos_token": {
|
12 |
+
"content": "</s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false
|
17 |
+
},
|
18 |
+
"image_token": "<s>",
|
19 |
+
"pad_token": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
+
"unk_token": {
|
27 |
+
"content": "<unk>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": false,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|