echarlaix HF staff commited on
Commit
da88cbf
·
1 Parent(s): 25f30ac
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_vocab_size": 257152,
3
+ "architectures": [
4
+ "PaliGemmaForConditionalGeneration"
5
+ ],
6
+ "hidden_size": 2048,
7
+ "image_token_index": 0,
8
+ "model_type": "paligemma",
9
+ "projection_dim": 32,
10
+ "projector_hidden_act": "gelu",
11
+ "text_config": {
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "head_dim": 8,
14
+ "hidden_activation": "gelu_pytorch_tanh",
15
+ "hidden_dropout_prob": 0.1,
16
+ "hidden_size": 32,
17
+ "id2label": {
18
+ "0": "LABEL_0",
19
+ "1": "LABEL_1",
20
+ "2": "LABEL_2"
21
+ },
22
+ "intermediate_size": 37,
23
+ "is_training": true,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2
28
+ },
29
+ "max_position_embeddings": 512,
30
+ "model_type": "gemma",
31
+ "num_attention_heads": 4,
32
+ "num_choices": 4,
33
+ "num_hidden_layers": 2,
34
+ "num_image_tokens": 16,
35
+ "num_key_value_heads": 1,
36
+ "pad_token_id": 1,
37
+ "seq_length": 264,
38
+ "type_sequence_label_size": 2,
39
+ "type_vocab_size": 16,
40
+ "use_labels": true,
41
+ "use_token_type_ids": false,
42
+ "vocab_size": 257153
43
+ },
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.48.0.dev0",
46
+ "vision_config": {
47
+ "attention_dropout": 0.1,
48
+ "dropout": 0.1,
49
+ "hidden_size": 32,
50
+ "image_size": 20,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 37,
53
+ "is_training": true,
54
+ "model_type": "siglip_vision_model",
55
+ "num_attention_heads": 4,
56
+ "num_hidden_layers": 2,
57
+ "num_image_tokens": 4,
58
+ "num_key_value_heads": 1,
59
+ "patch_size": 5,
60
+ "projection_dim": 32,
61
+ "use_labels": true
62
+ },
63
+ "vision_feature_layer": -1,
64
+ "vision_feature_select_strategy": "default"
65
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.48.0.dev0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c21bf200000f738790ce4aaee64e1b48e8d1e5593f6db4bebaccbaf506114c
3
+ size 33071404
preprocessor_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "SiglipImageProcessor",
12
+ "image_seq_length": 256,
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "processor_class": "PaliGemmaProcessor",
19
+ "resample": 3,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 20,
23
+ "width": 20
24
+ }
25
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<image>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<bos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<eos>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<pad>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<unk>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff