Hugging Face's logo

KaLM-Embedding
/
KaLM-Reranker-V1-Large

Text Ranking
sentence-transformers
Safetensors
Transformers
multilingual
t5gemma2
text2text-generation
reranker
encoder-decoder
FBNL
Retrieval
RAG
Model card Files
xet
 Community
2
Yuki131 commited on
Commit
c8d34de
·
verified ·
1 Parent(s): 08d0c1b

Upload 4 files

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. config.json +255 -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 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2560,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 10240,
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
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "full_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "full_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention"
57
+ ],
58
+ "max_position_embeddings": 131072,
59
+ "model_type": "t5gemma2_decoder",
60
+ "num_attention_heads": 8,
61
+ "num_hidden_layers": 34,
62
+ "num_key_value_heads": 4,
63
+ "pad_token_id": 0,
64
+ "query_pre_attn_scalar": 256,
65
+ "rms_norm_eps": 1e-06,
66
+ "rope_parameters": {
67
+ "full_attention": {
68
+ "factor": 8.0,
69
+ "rope_theta": 1000000,
70
+ "rope_type": "linear"
71
+ },
72
+ "sliding_attention": {
73
+ "rope_theta": 10000,
74
+ "rope_type": "default"
75
+ }
76
+ },
77
+ "sliding_window": 1024,
78
+ "use_bidirectional_attention": false,
79
+ "use_cache": true,
80
+ "vocab_size": 262144
81
+ },
82
+ "dtype": "bfloat16",
83
+ "encoder": {
84
+ "attention_dropout": 0.0,
85
+ "boi_token_index": 255999,
86
+ "dropout_rate": 0.0,
87
+ "dtype": "bfloat16",
88
+ "eoi_token_index": 256000,
89
+ "image_token_index": 256001,
90
+ "initializer_range": 0.02,
91
+ "mm_tokens_per_image": 256,
92
+ "model_type": "t5gemma2_encoder",
93
+ "text_config": {
94
+ "_name_or_path": "",
95
+ "_sliding_window_pattern": 6,
96
+ "add_cross_attention": false,
97
+ "architectures": null,
98
+ "attention_bias": false,
99
+ "attention_dropout": 0.0,
100
+ "attn_logit_softcapping": null,
101
+ "bos_token_id": 2,
102
+ "chunk_size_feed_forward": 0,
103
+ "cross_attention_hidden_size": null,
104
+ "decoder_start_token_id": null,
105
+ "dropout_rate": 0.0,
106
+ "dtype": "bfloat16",
107
+ "eos_token_id": 1,
108
+ "final_logit_softcapping": null,
109
+ "finetuning_task": null,
110
+ "head_dim": 256,
111
+ "hidden_activation": "gelu_pytorch_tanh",
112
+ "hidden_size": 2560,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 10240,
119
+ "is_decoder": false,
120
+ "is_encoder_decoder": false,
121
+ "label2id": {
122
+ "LABEL_0": 0,
123
+ "LABEL_1": 1
124
+ },
125
+ "layer_types": [
126
+ "sliding_attention",
127
+ "sliding_attention",
128
+ "sliding_attention",
129
+ "sliding_attention",
130
+ "sliding_attention",
131
+ "full_attention",
132
+ "sliding_attention",
133
+ "sliding_attention",
134
+ "sliding_attention",
135
+ "sliding_attention",
136
+ "sliding_attention",
137
+ "full_attention",
138
+ "sliding_attention",
139
+ "sliding_attention",
140
+ "sliding_attention",
141
+ "sliding_attention",
142
+ "sliding_attention",
143
+ "full_attention",
144
+ "sliding_attention",
145
+ "sliding_attention",
146
+ "sliding_attention",
147
+ "sliding_attention",
148
+ "sliding_attention",
149
+ "full_attention",
150
+ "sliding_attention",
151
+ "sliding_attention",
152
+ "sliding_attention",
153
+ "sliding_attention",
154
+ "sliding_attention",
155
+ "full_attention",
156
+ "sliding_attention",
157
+ "sliding_attention",
158
+ "sliding_attention",
159
+ "sliding_attention"
160
+ ],
161
+ "max_position_embeddings": 131072,
162
+ "model_type": "t5gemma2_text",
163
+ "num_attention_heads": 8,
164
+ "num_hidden_layers": 34,
165
+ "num_key_value_heads": 4,
166
+ "output_attentions": false,
167
+ "output_hidden_states": false,
168
+ "pad_token_id": 0,
169
+ "prefix": null,
170
+ "problem_type": null,
171
+ "query_pre_attn_scalar": 256,
172
+ "return_dict": true,
173
+ "rms_norm_eps": 1e-06,
174
+ "rope_parameters": {
175
+ "full_attention": {
176
+ "factor": 8.0,
177
+ "rope_theta": 1000000,
178
+ "rope_type": "linear"
179
+ },
180
+ "sliding_attention": {
181
+ "rope_theta": 10000,
182
+ "rope_type": "default"
183
+ }
184
+ },
185
+ "sep_token_id": null,
186
+ "sliding_window": 1024,
187
+ "task_specific_params": null,
188
+ "tie_encoder_decoder": false,
189
+ "tie_word_embeddings": true,
190
+ "tokenizer_class": null,
191
+ "use_bidirectional_attention": false,
192
+ "use_cache": true,
193
+ "vocab_size": 262144
194
+ },
195
+ "tie_word_embeddings": true,
196
+ "vision_config": {
197
+ "_name_or_path": "",
198
+ "add_cross_attention": false,
199
+ "architectures": null,
200
+ "attention_dropout": 0.0,
201
+ "bos_token_id": null,
202
+ "chunk_size_feed_forward": 0,
203
+ "cross_attention_hidden_size": null,
204
+ "decoder_start_token_id": null,
205
+ "dropout_rate": 0.0,
206
+ "dtype": "bfloat16",
207
+ "eos_token_id": null,
208
+ "finetuning_task": null,
209
+ "hidden_act": "gelu_pytorch_tanh",
210
+ "hidden_size": 1152,
211
+ "id2label": {
212
+ "0": "LABEL_0",
213
+ "1": "LABEL_1"
214
+ },
215
+ "image_size": 896,
216
+ "intermediate_size": 4304,
217
+ "is_decoder": false,
218
+ "is_encoder_decoder": false,
219
+ "label2id": {
220
+ "LABEL_0": 0,
221
+ "LABEL_1": 1
222
+ },
223
+ "layer_norm_eps": 1e-06,
224
+ "model_type": "siglip_vision_model",
225
+ "num_attention_heads": 16,
226
+ "num_channels": 3,
227
+ "num_hidden_layers": 27,
228
+ "output_attentions": false,
229
+ "output_hidden_states": false,
230
+ "pad_token_id": null,
231
+ "patch_size": 14,
232
+ "prefix": null,
233
+ "problem_type": null,
234
+ "return_dict": true,
235
+ "sep_token_id": null,
236
+ "task_specific_params": null,
237
+ "tie_encoder_decoder": false,
238
+ "tie_word_embeddings": true,
239
+ "tokenizer_class": null,
240
+ "vision_use_head": false,
241
+ "vocab_size": 262144
242
+ },
243
+ "vocab_size": 262144
244
+ },
245
+ "eoi_token_index": 256000,
246
+ "eos_token_id": 1,
247
+ "image_token_index": 256001,
248
+ "initializer_range": 0.02,
249
+ "is_encoder_decoder": true,
250
+ "model_type": "t5gemma2",
251
+ "pad_token_id": 0,
252
+ "tie_word_embeddings": true,
253
+ "transformers_version": "5.3.0",
254
+ "vocab_size": 262144
255
+ }
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
+ }