hf-transformers-bot commited on
Commit
bb39660
·
verified ·
1 Parent(s): cfb629f

Update tiny models for T5Gemma2Encoder

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* 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
 
 
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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5Gemma2Encoder"
4
+ ],
5
+ "boi_token_index": 5,
6
+ "dtype": "float32",
7
+ "eoi_token_index": 6,
8
+ "hidden_size": 32,
9
+ "image_token_index": 4,
10
+ "initializer_range": 0.02,
11
+ "mm_tokens_per_image": 2,
12
+ "model_type": "t5gemma2_encoder",
13
+ "text_config": {
14
+ "attention_bias": false,
15
+ "attention_dropout": 0.0,
16
+ "attention_probs_dropout_prob": 0.1,
17
+ "attn_logit_softcapping": null,
18
+ "bos_token_id": 2,
19
+ "dropout_rate": 0.0,
20
+ "eos_token_id": 1,
21
+ "final_logit_softcapping": null,
22
+ "head_dim": 8,
23
+ "hidden_act": "gelu",
24
+ "hidden_activation": "gelu_pytorch_tanh",
25
+ "hidden_dropout_prob": 0.1,
26
+ "hidden_size": 32,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 37,
29
+ "is_decoder": false,
30
+ "layer_types": [
31
+ "full_attention",
32
+ "sliding_attention"
33
+ ],
34
+ "max_position_embeddings": 512,
35
+ "model_type": "t5gemma2_text",
36
+ "num_attention_heads": 4,
37
+ "num_hidden_layers": 2,
38
+ "num_key_value_heads": 2,
39
+ "pad_token_id": 0,
40
+ "query_pre_attn_scalar": 256,
41
+ "rms_norm_eps": 1e-06,
42
+ "rope_parameters": {
43
+ "full_attention": {
44
+ "rope_theta": 1000000.0,
45
+ "rope_type": "default"
46
+ },
47
+ "sliding_attention": {
48
+ "rope_theta": 10000.0,
49
+ "rope_type": "default"
50
+ }
51
+ },
52
+ "sliding_window": 4096,
53
+ "tie_word_embeddings": true,
54
+ "type_vocab_size": 16,
55
+ "use_cache": true,
56
+ "vocab_size": 262144
57
+ },
58
+ "tie_word_embeddings": true,
59
+ "transformers_version": "5.16.0.dev0",
60
+ "vision_config": {
61
+ "attention_dropout": 0.0,
62
+ "dropout": 0.1,
63
+ "hidden_act": "gelu_pytorch_tanh",
64
+ "hidden_size": 32,
65
+ "image_size": 20,
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 37,
68
+ "is_training": true,
69
+ "layer_norm_eps": 1e-06,
70
+ "model_type": "siglip_vision_model",
71
+ "num_attention_heads": 4,
72
+ "num_channels": 3,
73
+ "num_hidden_layers": 2,
74
+ "num_key_value_heads": 1,
75
+ "patch_size": 5,
76
+ "use_labels": true
77
+ }
78
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d16ad6698391a63ba178c46788b6b2dbdb3f84bafe5a352dfed06036031338e
3
+ size 33715028
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 20,
4
+ "width": 20
5
+ },
6
+ "do_convert_rgb": true,
7
+ "do_normalize": true,
8
+ "do_rescale": true,
9
+ "do_resize": true,
10
+ "image_mean": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "image_processor_type": "Gemma3ImageProcessor",
16
+ "image_std": [
17
+ 0.5,
18
+ 0.5,
19
+ 0.5
20
+ ],
21
+ "resample": 2,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "height": 20,
25
+ "width": 20
26
+ }
27
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b325224482ec441ec5fbe2a5ac08c3758e0f9605f6e54368e31f736fcfb01d
3
+ size 33384387
tokenizer_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "boi_token": "<start_of_image>",
4
+ "bos_token": "<bos>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eoi_token": "<end_of_image>",
7
+ "eos_token": "<eos>",
8
+ "extra_special_tokens": [],
9
+ "image_token": "<image_soft_token>",
10
+ "is_local": true,
11
+ "local_files_only": false,
12
+ "mask_token": "<mask>",
13
+ "model_max_length": 1000000000000000019884624838656,
14
+ "model_specific_special_tokens": {
15
+ "boi_token": "<start_of_image>",
16
+ "eoi_token": "<end_of_image>",
17
+ "image_token": "<image_soft_token>"
18
+ },
19
+ "pad_token": "<pad>",
20
+ "padding_side": "right",
21
+ "processor_class": "Gemma3Processor",
22
+ "sp_model_kwargs": null,
23
+ "spaces_between_special_tokens": false,
24
+ "tokenizer_class": "GemmaTokenizer",
25
+ "unk_token": "<unk>",
26
+ "use_default_system_prompt": false
27
+ }