Text Ranking
sentence-transformers
Safetensors
Transformers
multilingual
t5gemma2
text2text-generation
reranker
encoder-decoder
FBNL
Retrieval
RAG
Yuki131 commited on
Commit
efc40be
·
verified ·
1 Parent(s): f4298c3

Upload 4 files

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. config.json +223 -0
  3. generation_config.json +10 -0
  4. tokenizer.json +3 -0
  5. tokenizer_config.json +26 -0
.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 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5Gemma2ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": 2,
6
+ "classifier_dropout_rate": 0.0,
7
+ "decoder": {
8
+ "_sliding_window_pattern": 6,
9
+ "attention_bias": false,
10
+ "attention_dropout": 0.0,
11
+ "attn_logit_softcapping": null,
12
+ "bos_token_id": 2,
13
+ "dropout_rate": 0.0,
14
+ "dtype": "bfloat16",
15
+ "eos_token_id": 1,
16
+ "final_logit_softcapping": null,
17
+ "head_dim": 256,
18
+ "hidden_activation": "gelu_pytorch_tanh",
19
+ "hidden_size": 640,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 2048,
22
+ "layer_types": [
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "sliding_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "full_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 32768,
43
+ "model_type": "t5gemma2_decoder",
44
+ "num_attention_heads": 4,
45
+ "num_hidden_layers": 18,
46
+ "num_key_value_heads": 1,
47
+ "pad_token_id": 0,
48
+ "query_pre_attn_scalar": 256,
49
+ "rms_norm_eps": 1e-06,
50
+ "rope_parameters": {
51
+ "full_attention": {
52
+ "factor": 8.0,
53
+ "rope_theta": 1000000,
54
+ "rope_type": "linear"
55
+ },
56
+ "sliding_attention": {
57
+ "rope_theta": 10000,
58
+ "rope_type": "default"
59
+ }
60
+ },
61
+ "sliding_window": 512,
62
+ "use_bidirectional_attention": false,
63
+ "use_cache": true,
64
+ "vocab_size": 262144
65
+ },
66
+ "dtype": "bfloat16",
67
+ "encoder": {
68
+ "attention_dropout": 0.0,
69
+ "boi_token_index": 255999,
70
+ "dropout_rate": 0.0,
71
+ "dtype": "bfloat16",
72
+ "eoi_token_index": 256000,
73
+ "image_token_index": 256001,
74
+ "initializer_range": 0.02,
75
+ "mm_tokens_per_image": 256,
76
+ "model_type": "t5gemma2_encoder",
77
+ "text_config": {
78
+ "_name_or_path": "",
79
+ "_sliding_window_pattern": 6,
80
+ "add_cross_attention": false,
81
+ "architectures": null,
82
+ "attention_bias": false,
83
+ "attention_dropout": 0.0,
84
+ "attn_logit_softcapping": null,
85
+ "bos_token_id": 2,
86
+ "chunk_size_feed_forward": 0,
87
+ "cross_attention_hidden_size": null,
88
+ "decoder_start_token_id": null,
89
+ "dropout_rate": 0.0,
90
+ "dtype": "bfloat16",
91
+ "eos_token_id": 1,
92
+ "final_logit_softcapping": null,
93
+ "finetuning_task": null,
94
+ "head_dim": 256,
95
+ "hidden_activation": "gelu_pytorch_tanh",
96
+ "hidden_size": 640,
97
+ "id2label": {
98
+ "0": "LABEL_0",
99
+ "1": "LABEL_1"
100
+ },
101
+ "initializer_range": 0.02,
102
+ "intermediate_size": 2048,
103
+ "is_decoder": false,
104
+ "is_encoder_decoder": false,
105
+ "label2id": {
106
+ "LABEL_0": 0,
107
+ "LABEL_1": 1
108
+ },
109
+ "layer_types": [
110
+ "sliding_attention",
111
+ "sliding_attention",
112
+ "sliding_attention",
113
+ "sliding_attention",
114
+ "sliding_attention",
115
+ "full_attention",
116
+ "sliding_attention",
117
+ "sliding_attention",
118
+ "sliding_attention",
119
+ "sliding_attention",
120
+ "sliding_attention",
121
+ "full_attention",
122
+ "sliding_attention",
123
+ "sliding_attention",
124
+ "sliding_attention",
125
+ "sliding_attention",
126
+ "sliding_attention",
127
+ "full_attention"
128
+ ],
129
+ "max_position_embeddings": 32768,
130
+ "model_type": "t5gemma2_text",
131
+ "num_attention_heads": 4,
132
+ "num_hidden_layers": 18,
133
+ "num_key_value_heads": 1,
134
+ "output_attentions": false,
135
+ "output_hidden_states": false,
136
+ "pad_token_id": 0,
137
+ "prefix": null,
138
+ "problem_type": null,
139
+ "query_pre_attn_scalar": 256,
140
+ "return_dict": true,
141
+ "rms_norm_eps": 1e-06,
142
+ "rope_parameters": {
143
+ "full_attention": {
144
+ "factor": 8.0,
145
+ "rope_theta": 1000000,
146
+ "rope_type": "linear"
147
+ },
148
+ "sliding_attention": {
149
+ "rope_theta": 10000,
150
+ "rope_type": "default"
151
+ }
152
+ },
153
+ "sep_token_id": null,
154
+ "sliding_window": 512,
155
+ "task_specific_params": null,
156
+ "tie_encoder_decoder": false,
157
+ "tie_word_embeddings": true,
158
+ "tokenizer_class": null,
159
+ "use_bidirectional_attention": false,
160
+ "use_cache": true,
161
+ "vocab_size": 262144
162
+ },
163
+ "tie_word_embeddings": true,
164
+ "vision_config": {
165
+ "_name_or_path": "",
166
+ "add_cross_attention": false,
167
+ "architectures": null,
168
+ "attention_dropout": 0.0,
169
+ "bos_token_id": null,
170
+ "chunk_size_feed_forward": 0,
171
+ "cross_attention_hidden_size": null,
172
+ "decoder_start_token_id": null,
173
+ "dropout_rate": 0.0,
174
+ "dtype": "bfloat16",
175
+ "eos_token_id": null,
176
+ "finetuning_task": null,
177
+ "hidden_act": "gelu_pytorch_tanh",
178
+ "hidden_size": 1152,
179
+ "id2label": {
180
+ "0": "LABEL_0",
181
+ "1": "LABEL_1"
182
+ },
183
+ "image_size": 896,
184
+ "intermediate_size": 4304,
185
+ "is_decoder": false,
186
+ "is_encoder_decoder": false,
187
+ "label2id": {
188
+ "LABEL_0": 0,
189
+ "LABEL_1": 1
190
+ },
191
+ "layer_norm_eps": 1e-06,
192
+ "model_type": "siglip_vision_model",
193
+ "num_attention_heads": 16,
194
+ "num_channels": 3,
195
+ "num_hidden_layers": 27,
196
+ "output_attentions": false,
197
+ "output_hidden_states": false,
198
+ "pad_token_id": null,
199
+ "patch_size": 14,
200
+ "prefix": null,
201
+ "problem_type": null,
202
+ "return_dict": true,
203
+ "sep_token_id": null,
204
+ "task_specific_params": null,
205
+ "tie_encoder_decoder": false,
206
+ "tie_word_embeddings": true,
207
+ "tokenizer_class": null,
208
+ "vision_use_head": false,
209
+ "vocab_size": 262144
210
+ },
211
+ "vocab_size": 262144
212
+ },
213
+ "eoi_token_index": 256000,
214
+ "eos_token_id": 1,
215
+ "image_token_index": 256001,
216
+ "initializer_range": 0.02,
217
+ "is_encoder_decoder": true,
218
+ "model_type": "t5gemma2",
219
+ "pad_token_id": 0,
220
+ "tie_word_embeddings": true,
221
+ "transformers_version": "5.3.0",
222
+ "vocab_size": 262144
223
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": 1,
6
+ "pad_token_id": 0,
7
+ "top_k": 64,
8
+ "top_p": 0.95,
9
+ "transformers_version": "5.3.0"
10
+ }
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 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "mask_token": "<mask>",
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "model_specific_special_tokens": {
14
+ "boi_token": "<start_of_image>",
15
+ "eoi_token": "<end_of_image>",
16
+ "image_token": "<image_soft_token>"
17
+ },
18
+ "pad_token": "<pad>",
19
+ "padding_side": "right",
20
+ "processor_class": "Gemma3Processor",
21
+ "sp_model_kwargs": null,
22
+ "spaces_between_special_tokens": false,
23
+ "tokenizer_class": "GemmaTokenizer",
24
+ "unk_token": "<unk>",
25
+ "use_default_system_prompt": false
26
+ }