endomorphosis commited on
Commit
3cee790
·
verified ·
1 Parent(s): 42ffdd4

Upload folder using huggingface_hub

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
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 151646,
3
+ "<|endoftext|>": 151643,
4
+ "<|im_end|>": 151645,
5
+ "<|im_start|>": 151644
6
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n'}}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ '\n' + content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ '\n' + content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{'<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "llava-hf/llava-interleave-qwen-0.5b-hf",
4
+ "architectures": [
5
+ "LlavaForConditionalGeneration"
6
+ ],
7
+ "ignore_index": -100,
8
+ "image_seq_length": 576,
9
+ "image_token_index": 151646,
10
+ "model_type": "llava",
11
+ "projector_hidden_act": "gelu",
12
+ "text_config": {
13
+ "_attn_implementation_autoset": false,
14
+ "_name_or_path": "Qwen/Qwen1.5-0.5B-Chat",
15
+ "add_cross_attention": false,
16
+ "architectures": [
17
+ "Qwen2ForCausalLM"
18
+ ],
19
+ "attention_dropout": 0.0,
20
+ "bad_words_ids": null,
21
+ "begin_suppress_tokens": null,
22
+ "bos_token_id": 151643,
23
+ "chunk_size_feed_forward": 0,
24
+ "cross_attention_hidden_size": null,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "early_stopping": false,
29
+ "encoder_no_repeat_ngram_size": 0,
30
+ "eos_token_id": 151645,
31
+ "exponential_decay_length_penalty": null,
32
+ "finetuning_task": null,
33
+ "forced_bos_token_id": null,
34
+ "forced_eos_token_id": null,
35
+ "hidden_act": "silu",
36
+ "hidden_size": 1024,
37
+ "id2label": {
38
+ "0": "LABEL_0",
39
+ "1": "LABEL_1"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 2816,
43
+ "is_decoder": false,
44
+ "is_encoder_decoder": false,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1
48
+ },
49
+ "length_penalty": 1.0,
50
+ "max_length": 20,
51
+ "max_position_embeddings": 32768,
52
+ "max_window_layers": 21,
53
+ "min_length": 0,
54
+ "model_type": "qwen2",
55
+ "no_repeat_ngram_size": 0,
56
+ "num_attention_heads": 16,
57
+ "num_beam_groups": 1,
58
+ "num_beams": 1,
59
+ "num_hidden_layers": 24,
60
+ "num_key_value_heads": 16,
61
+ "num_return_sequences": 1,
62
+ "output_attentions": false,
63
+ "output_hidden_states": false,
64
+ "output_scores": false,
65
+ "pad_token_id": null,
66
+ "prefix": null,
67
+ "problem_type": null,
68
+ "pruned_heads": {},
69
+ "remove_invalid_values": false,
70
+ "repetition_penalty": 1.0,
71
+ "return_dict": true,
72
+ "return_dict_in_generate": false,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sep_token_id": null,
77
+ "sliding_window": null,
78
+ "suppress_tokens": null,
79
+ "task_specific_params": null,
80
+ "temperature": 1.0,
81
+ "tf_legacy_loss": false,
82
+ "tie_encoder_decoder": false,
83
+ "tie_word_embeddings": true,
84
+ "tokenizer_class": null,
85
+ "top_k": 50,
86
+ "top_p": 1.0,
87
+ "torch_dtype": "bfloat16",
88
+ "torchscript": false,
89
+ "typical_p": 1.0,
90
+ "use_bfloat16": false,
91
+ "use_cache": true,
92
+ "use_sliding_window": false,
93
+ "vocab_size": 152000
94
+ },
95
+ "torch_dtype": "bfloat16",
96
+ "transformers_version": "4.46.3",
97
+ "vision_config": {
98
+ "_attn_implementation_autoset": false,
99
+ "_name_or_path": "",
100
+ "add_cross_attention": false,
101
+ "architectures": null,
102
+ "attention_dropout": 0.0,
103
+ "bad_words_ids": null,
104
+ "begin_suppress_tokens": null,
105
+ "bos_token_id": null,
106
+ "chunk_size_feed_forward": 0,
107
+ "cross_attention_hidden_size": null,
108
+ "decoder_start_token_id": null,
109
+ "diversity_penalty": 0.0,
110
+ "do_sample": false,
111
+ "early_stopping": false,
112
+ "encoder_no_repeat_ngram_size": 0,
113
+ "eos_token_id": null,
114
+ "exponential_decay_length_penalty": null,
115
+ "finetuning_task": null,
116
+ "forced_bos_token_id": null,
117
+ "forced_eos_token_id": null,
118
+ "hidden_act": "gelu_pytorch_tanh",
119
+ "hidden_size": 1152,
120
+ "id2label": {
121
+ "0": "LABEL_0",
122
+ "1": "LABEL_1"
123
+ },
124
+ "image_size": 384,
125
+ "intermediate_size": 4304,
126
+ "is_decoder": false,
127
+ "is_encoder_decoder": false,
128
+ "label2id": {
129
+ "LABEL_0": 0,
130
+ "LABEL_1": 1
131
+ },
132
+ "layer_norm_eps": 1e-06,
133
+ "length_penalty": 1.0,
134
+ "max_length": 20,
135
+ "min_length": 0,
136
+ "model_type": "siglip_vision_model",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 16,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_channels": 3,
142
+ "num_hidden_layers": 26,
143
+ "num_return_sequences": 1,
144
+ "output_attentions": false,
145
+ "output_hidden_states": false,
146
+ "output_scores": false,
147
+ "pad_token_id": null,
148
+ "patch_size": 14,
149
+ "prefix": null,
150
+ "problem_type": null,
151
+ "pruned_heads": {},
152
+ "remove_invalid_values": false,
153
+ "repetition_penalty": 1.0,
154
+ "return_dict": true,
155
+ "return_dict_in_generate": false,
156
+ "sep_token_id": null,
157
+ "suppress_tokens": null,
158
+ "task_specific_params": null,
159
+ "temperature": 1.0,
160
+ "tf_legacy_loss": false,
161
+ "tie_encoder_decoder": false,
162
+ "tie_word_embeddings": true,
163
+ "tokenizer_class": null,
164
+ "top_k": 50,
165
+ "top_p": 1.0,
166
+ "torch_dtype": null,
167
+ "torchscript": false,
168
+ "typical_p": 1.0,
169
+ "use_bfloat16": false,
170
+ "vision_use_head": false
171
+ },
172
+ "vision_feature_layer": -1,
173
+ "vision_feature_select_strategy": "full"
174
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.46.3"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09d602a890ac595abc484490f95694aaca98bd0d7a553ed23a8101f5abc5582
3
+ size 1582607
openvino_detokenizer.xml ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_58924" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_58924">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_58935" type="Convert" version="opset1">
14
+ <data destination_type="i32" />
15
+ <input>
16
+ <port id="0" precision="I64">
17
+ <dim>-1</dim>
18
+ <dim>-1</dim>
19
+ </port>
20
+ </input>
21
+ <output>
22
+ <port id="1" precision="I32">
23
+ <dim>-1</dim>
24
+ <dim>-1</dim>
25
+ </port>
26
+ </output>
27
+ </layer>
28
+ <layer id="2" name="Constant_58899" type="Const" version="opset1">
29
+ <data element_type="u8" shape="1582607" offset="0" size="1582607" />
30
+ <output>
31
+ <port id="0" precision="U8">
32
+ <dim>1582607</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="StringTensorUnpack_58900" type="StringTensorUnpack" version="extension">
37
+ <data mode="begins_ends" />
38
+ <input>
39
+ <port id="0" precision="U8">
40
+ <dim>1582607</dim>
41
+ </port>
42
+ </input>
43
+ <output>
44
+ <port id="1" precision="I32">
45
+ <dim>-1</dim>
46
+ </port>
47
+ <port id="2" precision="I32">
48
+ <dim>-1</dim>
49
+ </port>
50
+ <port id="3" precision="U8">
51
+ <dim>-1</dim>
52
+ </port>
53
+ </output>
54
+ </layer>
55
+ <layer id="4" name="VocabDecoder_58925" type="VocabDecoder" version="extension">
56
+ <data skip_tokens="151643, 151644, 151645, 151646" />
57
+ <input>
58
+ <port id="0" precision="I32">
59
+ <dim>-1</dim>
60
+ <dim>-1</dim>
61
+ </port>
62
+ <port id="1" precision="I32">
63
+ <dim>-1</dim>
64
+ </port>
65
+ <port id="2" precision="I32">
66
+ <dim>-1</dim>
67
+ </port>
68
+ <port id="3" precision="U8">
69
+ <dim>-1</dim>
70
+ </port>
71
+ </input>
72
+ <output>
73
+ <port id="4" precision="I32">
74
+ <dim>-1</dim>
75
+ </port>
76
+ <port id="5" precision="I32">
77
+ <dim>-1</dim>
78
+ </port>
79
+ <port id="6" precision="I32">
80
+ <dim>-1</dim>
81
+ </port>
82
+ <port id="7" precision="I32">
83
+ <dim>-1</dim>
84
+ </port>
85
+ <port id="8" precision="U8">
86
+ <dim>-1</dim>
87
+ </port>
88
+ </output>
89
+ </layer>
90
+ <layer id="5" name="FuzeRagged_58926" type="FuzeRagged" version="extension">
91
+ <input>
92
+ <port id="0" precision="I32">
93
+ <dim>-1</dim>
94
+ </port>
95
+ <port id="1" precision="I32">
96
+ <dim>-1</dim>
97
+ </port>
98
+ <port id="2" precision="I32">
99
+ <dim>-1</dim>
100
+ </port>
101
+ <port id="3" precision="I32">
102
+ <dim>-1</dim>
103
+ </port>
104
+ </input>
105
+ <output>
106
+ <port id="4" precision="I32">
107
+ <dim>-1</dim>
108
+ </port>
109
+ <port id="5" precision="I32">
110
+ <dim>-1</dim>
111
+ </port>
112
+ </output>
113
+ </layer>
114
+ <layer id="6" name="StringTensorPack_58927" type="StringTensorPack" version="extension">
115
+ <data mode="begins_ends" />
116
+ <input>
117
+ <port id="0" precision="I32">
118
+ <dim>-1</dim>
119
+ </port>
120
+ <port id="1" precision="I32">
121
+ <dim>-1</dim>
122
+ </port>
123
+ <port id="2" precision="U8">
124
+ <dim>-1</dim>
125
+ </port>
126
+ </input>
127
+ <output>
128
+ <port id="3" precision="STRING" names="string_output">
129
+ <dim>-1</dim>
130
+ </port>
131
+ </output>
132
+ </layer>
133
+ <layer id="7" name="Result_58928" type="Result" version="opset1">
134
+ <input>
135
+ <port id="0" precision="STRING">
136
+ <dim>-1</dim>
137
+ </port>
138
+ </input>
139
+ </layer>
140
+ </layers>
141
+ <edges>
142
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
143
+ <edge from-layer="1" from-port="1" to-layer="4" to-port="0" />
144
+ <edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
145
+ <edge from-layer="3" from-port="1" to-layer="4" to-port="1" />
146
+ <edge from-layer="3" from-port="2" to-layer="4" to-port="2" />
147
+ <edge from-layer="3" from-port="3" to-layer="4" to-port="3" />
148
+ <edge from-layer="4" from-port="4" to-layer="5" to-port="0" />
149
+ <edge from-layer="4" from-port="5" to-layer="5" to-port="1" />
150
+ <edge from-layer="4" from-port="6" to-layer="5" to-port="2" />
151
+ <edge from-layer="4" from-port="7" to-layer="5" to-port="3" />
152
+ <edge from-layer="4" from-port="8" to-layer="6" to-port="2" />
153
+ <edge from-layer="5" from-port="4" to-layer="6" to-port="0" />
154
+ <edge from-layer="5" from-port="5" to-layer="6" to-port="1" />
155
+ <edge from-layer="6" from-port="3" to-layer="7" to-port="0" />
156
+ </edges>
157
+ <rt_info>
158
+ <add_attention_mask value="True" />
159
+ <add_prefix_space />
160
+ <add_special_tokens value="True" />
161
+ <chat_template value="{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '&lt;|im_start|>system&#10;You are a helpful assistant.&lt;|im_end|>&#10;' }}{% endif %}{{'&lt;|im_start|>' + message['role'] + '&#10;' + message['content'] + '&lt;|im_end|>' + '&#10;'}}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|im_start|>assistant&#10;' }}{% endif %}" />
162
+ <clean_up_tokenization_spaces />
163
+ <detokenizer_input_type value="i64" />
164
+ <eos_token_id value="151645" />
165
+ <handle_special_tokens_with_re />
166
+ <number_of_inputs value="1" />
167
+ <openvino_tokenizers_version value="2024.5.0.0" />
168
+ <openvino_version value="2024.5.0" />
169
+ <original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
170
+ <pad_token_id value="151643" />
171
+ <sentencepiece_version value="0.2.0" />
172
+ <skip_special_tokens value="True" />
173
+ <streaming_detokenizer value="False" />
174
+ <tiktoken_version value="0.8.0" />
175
+ <tokenizer_output_type value="i64" />
176
+ <tokenizers_version value="0.20.3" />
177
+ <transformers_version value="4.46.3" />
178
+ <use_max_padding value="False" />
179
+ <use_sentencepiece_backend value="False" />
180
+ <utf8_replace_mode />
181
+ <with_detokenizer value="True" />
182
+ </rt_info>
183
+ </net>
openvino_language_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eafe315802cafc172a4dc1a4f93aa9737db1ea4f49f1408b6a6eb6dcd57b6ca
3
+ size 928207192
openvino_language_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
openvino_text_embeddings_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e001727871141938ef9b535ea3ac40fa622f71389dcbba9d2c66efd856079b2
3
+ size 311296004
openvino_text_embeddings_model.xml ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="Model6" version="11">
3
+ <layers>
4
+ <layer id="0" name="input" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="input">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="self.weight" type="Const" version="opset1">
14
+ <data element_type="bf16" shape="152000, 1024" offset="0" size="311296000" />
15
+ <output>
16
+ <port id="0" precision="BF16" names="self.weight">
17
+ <dim>152000</dim>
18
+ <dim>1024</dim>
19
+ </port>
20
+ </output>
21
+ </layer>
22
+ <layer id="2" name="ov_ext::embedding/Convert" type="Convert" version="opset1">
23
+ <data destination_type="f32" />
24
+ <rt_info>
25
+ <attribute name="decompression" version="0" />
26
+ </rt_info>
27
+ <input>
28
+ <port id="0" precision="BF16">
29
+ <dim>152000</dim>
30
+ <dim>1024</dim>
31
+ </port>
32
+ </input>
33
+ <output>
34
+ <port id="1" precision="FP32">
35
+ <dim>152000</dim>
36
+ <dim>1024</dim>
37
+ </port>
38
+ </output>
39
+ </layer>
40
+ <layer id="3" name="ov_ext::embedding/Convert_1" type="Convert" version="opset1">
41
+ <data destination_type="i32" />
42
+ <input>
43
+ <port id="0" precision="I64">
44
+ <dim>-1</dim>
45
+ <dim>-1</dim>
46
+ </port>
47
+ </input>
48
+ <output>
49
+ <port id="1" precision="I32">
50
+ <dim>-1</dim>
51
+ <dim>-1</dim>
52
+ </port>
53
+ </output>
54
+ </layer>
55
+ <layer id="4" name="ov_ext::embedding/Constant" type="Const" version="opset1">
56
+ <data element_type="i32" shape="" offset="311296000" size="4" />
57
+ <output>
58
+ <port id="0" precision="I32" />
59
+ </output>
60
+ </layer>
61
+ <layer id="5" name="ov_ext::embedding/Gather" type="Gather" version="opset8">
62
+ <data batch_dims="0" />
63
+ <input>
64
+ <port id="0" precision="FP32">
65
+ <dim>152000</dim>
66
+ <dim>1024</dim>
67
+ </port>
68
+ <port id="1" precision="I32">
69
+ <dim>-1</dim>
70
+ <dim>-1</dim>
71
+ </port>
72
+ <port id="2" precision="I32" />
73
+ </input>
74
+ <output>
75
+ <port id="3" precision="FP32" names="inputs_embeds">
76
+ <dim>-1</dim>
77
+ <dim>-1</dim>
78
+ <dim>1024</dim>
79
+ </port>
80
+ </output>
81
+ </layer>
82
+ <layer id="6" name="Result_57074" type="Result" version="opset1">
83
+ <input>
84
+ <port id="0" precision="FP32">
85
+ <dim>-1</dim>
86
+ <dim>-1</dim>
87
+ <dim>1024</dim>
88
+ </port>
89
+ </input>
90
+ </layer>
91
+ </layers>
92
+ <edges>
93
+ <edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
94
+ <edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
95
+ <edge from-layer="2" from-port="1" to-layer="5" to-port="0" />
96
+ <edge from-layer="3" from-port="1" to-layer="5" to-port="1" />
97
+ <edge from-layer="4" from-port="0" to-layer="5" to-port="2" />
98
+ <edge from-layer="5" from-port="3" to-layer="6" to-port="0" />
99
+ </edges>
100
+ <rt_info>
101
+ <Runtime_version value="2024.5.0-17288-7975fa5da0c-refs/pull/3856/head" />
102
+ <conversion_parameters>
103
+ <framework value="pytorch" />
104
+ <is_python_object value="True" />
105
+ </conversion_parameters>
106
+ <optimum>
107
+ <optimum_intel_version value="1.22.0.dev0+35cf1d2" />
108
+ <optimum_version value="1.23.3" />
109
+ <pytorch_version value="2.3.0" />
110
+ <transformers_version value="4.46.3" />
111
+ </optimum>
112
+ </rt_info>
113
+ </net>
openvino_tokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a89130f86e48fb1d71369f57a35701f4fbc6592e0c405c464deb3158c7413bf
3
+ size 3769719
openvino_tokenizer.xml ADDED
@@ -0,0 +1,736 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_58817" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="Parameter_58817">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_58823" type="Const" version="opset1">
13
+ <data element_type="i64" shape="" offset="0" size="8" />
14
+ <output>
15
+ <port id="0" precision="I64" />
16
+ </output>
17
+ </layer>
18
+ <layer id="2" name="StringTensorUnpack_58818" type="StringTensorUnpack" version="extension">
19
+ <data mode="begins_ends" />
20
+ <input>
21
+ <port id="0" precision="STRING">
22
+ <dim>-1</dim>
23
+ </port>
24
+ </input>
25
+ <output>
26
+ <port id="1" precision="I32">
27
+ <dim>-1</dim>
28
+ </port>
29
+ <port id="2" precision="I32">
30
+ <dim>-1</dim>
31
+ </port>
32
+ <port id="3" precision="U8">
33
+ <dim>-1</dim>
34
+ </port>
35
+ </output>
36
+ </layer>
37
+ <layer id="3" name="ShapeOf_58819" type="ShapeOf" version="opset3">
38
+ <data output_type="i64" />
39
+ <input>
40
+ <port id="0" precision="I32">
41
+ <dim>-1</dim>
42
+ </port>
43
+ </input>
44
+ <output>
45
+ <port id="1" precision="I64">
46
+ <dim>1</dim>
47
+ </port>
48
+ </output>
49
+ </layer>
50
+ <layer id="4" name="Constant_58820" type="Const" version="opset1">
51
+ <data element_type="i64" shape="" offset="0" size="8" />
52
+ <output>
53
+ <port id="0" precision="I64" />
54
+ </output>
55
+ </layer>
56
+ <layer id="5" name="Constant_58821" type="Const" version="opset1">
57
+ <data element_type="i64" shape="" offset="0" size="8" />
58
+ <output>
59
+ <port id="0" precision="I64" />
60
+ </output>
61
+ </layer>
62
+ <layer id="6" name="Gather_58822" type="Gather" version="opset8">
63
+ <data batch_dims="0" />
64
+ <input>
65
+ <port id="0" precision="I64">
66
+ <dim>1</dim>
67
+ </port>
68
+ <port id="1" precision="I64" />
69
+ <port id="2" precision="I64" />
70
+ </input>
71
+ <output>
72
+ <port id="3" precision="I64" />
73
+ </output>
74
+ </layer>
75
+ <layer id="7" name="Constant_58824" type="Const" version="opset1">
76
+ <data element_type="i64" shape="" offset="8" size="8" />
77
+ <output>
78
+ <port id="0" precision="I64" />
79
+ </output>
80
+ </layer>
81
+ <layer id="8" name="Range_58825" type="Range" version="opset4">
82
+ <data output_type="i32" />
83
+ <input>
84
+ <port id="0" precision="I64" />
85
+ <port id="1" precision="I64" />
86
+ <port id="2" precision="I64" />
87
+ </input>
88
+ <output>
89
+ <port id="3" precision="I32">
90
+ <dim>-1</dim>
91
+ </port>
92
+ </output>
93
+ </layer>
94
+ <layer id="9" name="Constant_58826" type="Const" version="opset1">
95
+ <data element_type="i64" shape="" offset="8" size="8" />
96
+ <output>
97
+ <port id="0" precision="I64" />
98
+ </output>
99
+ </layer>
100
+ <layer id="10" name="Constant_58827" type="Const" version="opset1">
101
+ <data element_type="i64" shape="" offset="8" size="8" />
102
+ <output>
103
+ <port id="0" precision="I64" />
104
+ </output>
105
+ </layer>
106
+ <layer id="11" name="Add_58828" type="Add" version="opset1">
107
+ <data auto_broadcast="numpy" />
108
+ <input>
109
+ <port id="0" precision="I64" />
110
+ <port id="1" precision="I64" />
111
+ </input>
112
+ <output>
113
+ <port id="2" precision="I64" />
114
+ </output>
115
+ </layer>
116
+ <layer id="12" name="Constant_58829" type="Const" version="opset1">
117
+ <data element_type="i64" shape="" offset="8" size="8" />
118
+ <output>
119
+ <port id="0" precision="I64" />
120
+ </output>
121
+ </layer>
122
+ <layer id="13" name="Range_58830" type="Range" version="opset4">
123
+ <data output_type="i32" />
124
+ <input>
125
+ <port id="0" precision="I64" />
126
+ <port id="1" precision="I64" />
127
+ <port id="2" precision="I64" />
128
+ </input>
129
+ <output>
130
+ <port id="3" precision="I32">
131
+ <dim>-1</dim>
132
+ </port>
133
+ </output>
134
+ </layer>
135
+ <layer id="14" name="Constant_58892" type="Const" version="opset1">
136
+ <data element_type="u8" shape="67" offset="16" size="67" />
137
+ <output>
138
+ <port id="0" precision="U8">
139
+ <dim>67</dim>
140
+ </port>
141
+ </output>
142
+ </layer>
143
+ <layer id="15" name="SpecialTokensSplit_58893" type="SpecialTokensSplit" version="extension">
144
+ <input>
145
+ <port id="0" precision="I32">
146
+ <dim>-1</dim>
147
+ </port>
148
+ <port id="1" precision="I32">
149
+ <dim>-1</dim>
150
+ </port>
151
+ <port id="2" precision="I32">
152
+ <dim>-1</dim>
153
+ </port>
154
+ <port id="3" precision="I32">
155
+ <dim>-1</dim>
156
+ </port>
157
+ <port id="4" precision="U8">
158
+ <dim>-1</dim>
159
+ </port>
160
+ <port id="5" precision="U8">
161
+ <dim>67</dim>
162
+ </port>
163
+ </input>
164
+ <output>
165
+ <port id="6" precision="I32">
166
+ <dim>-1</dim>
167
+ </port>
168
+ <port id="7" precision="I32">
169
+ <dim>-1</dim>
170
+ </port>
171
+ <port id="8" precision="I32">
172
+ <dim>-1</dim>
173
+ </port>
174
+ <port id="9" precision="I32">
175
+ <dim>-1</dim>
176
+ </port>
177
+ <port id="10" precision="U8">
178
+ <dim>-1</dim>
179
+ </port>
180
+ <port id="11" precision="BOOL">
181
+ <dim>-1</dim>
182
+ </port>
183
+ </output>
184
+ </layer>
185
+ <layer id="16" name="NormalizeUnicode_58894" type="NormalizeUnicode" version="extension">
186
+ <data normalization_form="NFC" />
187
+ <input>
188
+ <port id="0" precision="I32">
189
+ <dim>-1</dim>
190
+ </port>
191
+ <port id="1" precision="I32">
192
+ <dim>-1</dim>
193
+ </port>
194
+ <port id="2" precision="U8">
195
+ <dim>-1</dim>
196
+ </port>
197
+ <port id="3" precision="BOOL">
198
+ <dim>-1</dim>
199
+ </port>
200
+ </input>
201
+ <output>
202
+ <port id="4" precision="I32">
203
+ <dim>-1</dim>
204
+ </port>
205
+ <port id="5" precision="I32">
206
+ <dim>-1</dim>
207
+ </port>
208
+ <port id="6" precision="U8">
209
+ <dim>-1</dim>
210
+ </port>
211
+ <port id="7" precision="BOOL">
212
+ <dim>-1</dim>
213
+ </port>
214
+ </output>
215
+ </layer>
216
+ <layer id="17" name="Constant_58896" type="Const" version="opset1">
217
+ <data element_type="u8" shape="110" offset="83" size="110" />
218
+ <output>
219
+ <port id="0" precision="U8">
220
+ <dim>110</dim>
221
+ </port>
222
+ </output>
223
+ </layer>
224
+ <layer id="18" name="RegexSplit_58897" type="RegexSplit" version="extension">
225
+ <data behaviour="isolate" invert="false" max_splits="-1" />
226
+ <input>
227
+ <port id="0" precision="I32">
228
+ <dim>-1</dim>
229
+ </port>
230
+ <port id="1" precision="I32">
231
+ <dim>-1</dim>
232
+ </port>
233
+ <port id="2" precision="I32">
234
+ <dim>-1</dim>
235
+ </port>
236
+ <port id="3" precision="I32">
237
+ <dim>-1</dim>
238
+ </port>
239
+ <port id="4" precision="U8">
240
+ <dim>-1</dim>
241
+ </port>
242
+ <port id="5" precision="BOOL">
243
+ <dim>-1</dim>
244
+ </port>
245
+ <port id="6" precision="U8">
246
+ <dim>110</dim>
247
+ </port>
248
+ </input>
249
+ <output>
250
+ <port id="7" precision="I32">
251
+ <dim>-1</dim>
252
+ </port>
253
+ <port id="8" precision="I32">
254
+ <dim>-1</dim>
255
+ </port>
256
+ <port id="9" precision="I32">
257
+ <dim>-1</dim>
258
+ </port>
259
+ <port id="10" precision="I32">
260
+ <dim>-1</dim>
261
+ </port>
262
+ <port id="11" precision="U8">
263
+ <dim>-1</dim>
264
+ </port>
265
+ <port id="12" precision="BOOL">
266
+ <dim>-1</dim>
267
+ </port>
268
+ </output>
269
+ </layer>
270
+ <layer id="19" name="Constant_58899" type="Const" version="opset1">
271
+ <data element_type="u8" shape="1582607" offset="193" size="1582607" />
272
+ <output>
273
+ <port id="0" precision="U8">
274
+ <dim>1582607</dim>
275
+ </port>
276
+ </output>
277
+ </layer>
278
+ <layer id="20" name="StringTensorUnpack_58900" type="StringTensorUnpack" version="extension">
279
+ <data mode="begins_ends" />
280
+ <input>
281
+ <port id="0" precision="U8">
282
+ <dim>1582607</dim>
283
+ </port>
284
+ </input>
285
+ <output>
286
+ <port id="1" precision="I32">
287
+ <dim>-1</dim>
288
+ </port>
289
+ <port id="2" precision="I32">
290
+ <dim>-1</dim>
291
+ </port>
292
+ <port id="3" precision="U8">
293
+ <dim>-1</dim>
294
+ </port>
295
+ </output>
296
+ </layer>
297
+ <layer id="21" name="Constant_58905" type="Const" version="opset1">
298
+ <data element_type="u8" shape="1096915" offset="1582800" size="1096915" />
299
+ <output>
300
+ <port id="0" precision="U8">
301
+ <dim>1096915</dim>
302
+ </port>
303
+ </output>
304
+ </layer>
305
+ <layer id="22" name="StringTensorUnpack_58906" type="StringTensorUnpack" version="extension">
306
+ <data mode="begins_ends" />
307
+ <input>
308
+ <port id="0" precision="U8">
309
+ <dim>1096915</dim>
310
+ </port>
311
+ </input>
312
+ <output>
313
+ <port id="1" precision="I32">
314
+ <dim>-1</dim>
315
+ </port>
316
+ <port id="2" precision="I32">
317
+ <dim>-1</dim>
318
+ </port>
319
+ <port id="3" precision="U8">
320
+ <dim>-1</dim>
321
+ </port>
322
+ </output>
323
+ </layer>
324
+ <layer id="23" name="Constant_58908" type="Const" version="opset1">
325
+ <data element_type="u8" shape="1089910" offset="2679715" size="1089910" />
326
+ <output>
327
+ <port id="0" precision="U8">
328
+ <dim>1089910</dim>
329
+ </port>
330
+ </output>
331
+ </layer>
332
+ <layer id="24" name="StringTensorUnpack_58909" type="StringTensorUnpack" version="extension">
333
+ <data mode="begins_ends" />
334
+ <input>
335
+ <port id="0" precision="U8">
336
+ <dim>1089910</dim>
337
+ </port>
338
+ </input>
339
+ <output>
340
+ <port id="1" precision="I32">
341
+ <dim>-1</dim>
342
+ </port>
343
+ <port id="2" precision="I32">
344
+ <dim>-1</dim>
345
+ </port>
346
+ <port id="3" precision="U8">
347
+ <dim>-1</dim>
348
+ </port>
349
+ </output>
350
+ </layer>
351
+ <layer id="25" name="Constant_58902" type="Const" version="opset1">
352
+ <data element_type="u8" shape="66" offset="3769625" size="66" />
353
+ <output>
354
+ <port id="0" precision="U8">
355
+ <dim>66</dim>
356
+ </port>
357
+ </output>
358
+ </layer>
359
+ <layer id="26" name="StringTensorUnpack_58903" type="StringTensorUnpack" version="extension">
360
+ <data mode="begins_ends" />
361
+ <input>
362
+ <port id="0" precision="U8">
363
+ <dim>66</dim>
364
+ </port>
365
+ </input>
366
+ <output>
367
+ <port id="1" precision="I32">
368
+ <dim>-1</dim>
369
+ </port>
370
+ <port id="2" precision="I32">
371
+ <dim>-1</dim>
372
+ </port>
373
+ <port id="3" precision="U8">
374
+ <dim>-1</dim>
375
+ </port>
376
+ </output>
377
+ </layer>
378
+ <layer id="27" name="Constant_58910" type="Const" version="opset1">
379
+ <data element_type="i32" shape="4" offset="3769691" size="16" />
380
+ <output>
381
+ <port id="0" precision="I32">
382
+ <dim>4</dim>
383
+ </port>
384
+ </output>
385
+ </layer>
386
+ <layer id="28" name="BPETokenizer_58911" type="BPETokenizer" version="extension">
387
+ <data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="30328" />
388
+ <input>
389
+ <port id="0" precision="I32">
390
+ <dim>-1</dim>
391
+ </port>
392
+ <port id="1" precision="I32">
393
+ <dim>-1</dim>
394
+ </port>
395
+ <port id="2" precision="I32">
396
+ <dim>-1</dim>
397
+ </port>
398
+ <port id="3" precision="I32">
399
+ <dim>-1</dim>
400
+ </port>
401
+ <port id="4" precision="U8">
402
+ <dim>-1</dim>
403
+ </port>
404
+ <port id="5" precision="I32">
405
+ <dim>-1</dim>
406
+ </port>
407
+ <port id="6" precision="I32">
408
+ <dim>-1</dim>
409
+ </port>
410
+ <port id="7" precision="U8">
411
+ <dim>-1</dim>
412
+ </port>
413
+ <port id="8" precision="I32">
414
+ <dim>-1</dim>
415
+ </port>
416
+ <port id="9" precision="I32">
417
+ <dim>-1</dim>
418
+ </port>
419
+ <port id="10" precision="U8">
420
+ <dim>-1</dim>
421
+ </port>
422
+ <port id="11" precision="I32">
423
+ <dim>-1</dim>
424
+ </port>
425
+ <port id="12" precision="I32">
426
+ <dim>-1</dim>
427
+ </port>
428
+ <port id="13" precision="U8">
429
+ <dim>-1</dim>
430
+ </port>
431
+ <port id="14" precision="I32">
432
+ <dim>-1</dim>
433
+ </port>
434
+ <port id="15" precision="I32">
435
+ <dim>-1</dim>
436
+ </port>
437
+ <port id="16" precision="U8">
438
+ <dim>-1</dim>
439
+ </port>
440
+ <port id="17" precision="I32">
441
+ <dim>4</dim>
442
+ </port>
443
+ </input>
444
+ <output>
445
+ <port id="18" precision="I32">
446
+ <dim>-1</dim>
447
+ </port>
448
+ <port id="19" precision="I32">
449
+ <dim>-1</dim>
450
+ </port>
451
+ <port id="20" precision="I32">
452
+ <dim>-1</dim>
453
+ </port>
454
+ </output>
455
+ </layer>
456
+ <layer id="29" name="Subtract_58912" type="Subtract" version="opset1">
457
+ <data auto_broadcast="numpy" />
458
+ <input>
459
+ <port id="0" precision="I32">
460
+ <dim>-1</dim>
461
+ </port>
462
+ <port id="1" precision="I32">
463
+ <dim>-1</dim>
464
+ </port>
465
+ </input>
466
+ <output>
467
+ <port id="2" precision="I32">
468
+ <dim>-1</dim>
469
+ </port>
470
+ </output>
471
+ </layer>
472
+ <layer id="30" name="Constant_58913" type="Const" version="opset1">
473
+ <data element_type="i32" shape="" offset="3769707" size="4" />
474
+ <output>
475
+ <port id="0" precision="I32" />
476
+ </output>
477
+ </layer>
478
+ <layer id="31" name="Minimum_58914" type="Minimum" version="opset1">
479
+ <data auto_broadcast="numpy" />
480
+ <input>
481
+ <port id="0" precision="I32">
482
+ <dim>-1</dim>
483
+ </port>
484
+ <port id="1" precision="I32" />
485
+ </input>
486
+ <output>
487
+ <port id="2" precision="I32">
488
+ <dim>-1</dim>
489
+ </port>
490
+ </output>
491
+ </layer>
492
+ <layer id="32" name="Add_58915" type="Add" version="opset1">
493
+ <data auto_broadcast="numpy" />
494
+ <input>
495
+ <port id="0" precision="I32">
496
+ <dim>-1</dim>
497
+ </port>
498
+ <port id="1" precision="I32">
499
+ <dim>-1</dim>
500
+ </port>
501
+ </input>
502
+ <output>
503
+ <port id="2" precision="I32">
504
+ <dim>-1</dim>
505
+ </port>
506
+ </output>
507
+ </layer>
508
+ <layer id="33" name="Subtract_58916" type="Subtract" version="opset1">
509
+ <data auto_broadcast="numpy" />
510
+ <input>
511
+ <port id="0" precision="I32">
512
+ <dim>-1</dim>
513
+ </port>
514
+ <port id="1" precision="I32">
515
+ <dim>-1</dim>
516
+ </port>
517
+ </input>
518
+ <output>
519
+ <port id="2" precision="I32">
520
+ <dim>-1</dim>
521
+ </port>
522
+ </output>
523
+ </layer>
524
+ <layer id="34" name="Constant_58917" type="Const" version="opset1">
525
+ <data element_type="i32" shape="" offset="3769711" size="4" />
526
+ <output>
527
+ <port id="0" precision="I32" />
528
+ </output>
529
+ </layer>
530
+ <layer id="35" name="ReduceMax_58918" type="ReduceMax" version="opset1">
531
+ <data keep_dims="false" />
532
+ <input>
533
+ <port id="0" precision="I32">
534
+ <dim>-1</dim>
535
+ </port>
536
+ <port id="1" precision="I32" />
537
+ </input>
538
+ <output>
539
+ <port id="2" precision="I32" />
540
+ </output>
541
+ </layer>
542
+ <layer id="36" name="Constant_58919" type="Const" version="opset1">
543
+ <data element_type="i32" shape="" offset="3769715" size="4" />
544
+ <output>
545
+ <port id="0" precision="I32" />
546
+ </output>
547
+ </layer>
548
+ <layer id="37" name="RaggedToDense_58920" type="RaggedToDense" version="extension">
549
+ <data pad_right="true" />
550
+ <input>
551
+ <port id="0" precision="I32">
552
+ <dim>-1</dim>
553
+ </port>
554
+ <port id="1" precision="I32">
555
+ <dim>-1</dim>
556
+ </port>
557
+ <port id="2" precision="I32">
558
+ <dim>-1</dim>
559
+ </port>
560
+ <port id="3" precision="I32" />
561
+ <port id="4" precision="I32" />
562
+ </input>
563
+ <output>
564
+ <port id="5" precision="I32">
565
+ <dim>-1</dim>
566
+ <dim>-1</dim>
567
+ </port>
568
+ <port id="6" precision="BOOL">
569
+ <dim>-1</dim>
570
+ <dim>-1</dim>
571
+ </port>
572
+ </output>
573
+ </layer>
574
+ <layer id="38" name="Convert_58921" type="Convert" version="opset1">
575
+ <data destination_type="i32" />
576
+ <input>
577
+ <port id="0" precision="BOOL">
578
+ <dim>-1</dim>
579
+ <dim>-1</dim>
580
+ </port>
581
+ </input>
582
+ <output>
583
+ <port id="1" precision="I32">
584
+ <dim>-1</dim>
585
+ <dim>-1</dim>
586
+ </port>
587
+ </output>
588
+ </layer>
589
+ <layer id="39" name="Convert_58921" type="Convert" version="opset1">
590
+ <data destination_type="i64" />
591
+ <input>
592
+ <port id="0" precision="I32">
593
+ <dim>-1</dim>
594
+ <dim>-1</dim>
595
+ </port>
596
+ </input>
597
+ <output>
598
+ <port id="1" precision="I64" names="attention_mask">
599
+ <dim>-1</dim>
600
+ <dim>-1</dim>
601
+ </port>
602
+ </output>
603
+ </layer>
604
+ <layer id="41" name="RaggedToDense_58920.0" type="Convert" version="opset1">
605
+ <data destination_type="i64" />
606
+ <input>
607
+ <port id="0" precision="I32">
608
+ <dim>-1</dim>
609
+ <dim>-1</dim>
610
+ </port>
611
+ </input>
612
+ <output>
613
+ <port id="1" precision="I64" names="input_ids">
614
+ <dim>-1</dim>
615
+ <dim>-1</dim>
616
+ </port>
617
+ </output>
618
+ </layer>
619
+ <layer id="42" name="Result_58922" type="Result" version="opset1">
620
+ <input>
621
+ <port id="0" precision="I64">
622
+ <dim>-1</dim>
623
+ <dim>-1</dim>
624
+ </port>
625
+ </input>
626
+ </layer>
627
+ <layer id="40" name="Result_58923" type="Result" version="opset1">
628
+ <input>
629
+ <port id="0" precision="I64">
630
+ <dim>-1</dim>
631
+ <dim>-1</dim>
632
+ </port>
633
+ </input>
634
+ </layer>
635
+ </layers>
636
+ <edges>
637
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
638
+ <edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
639
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
640
+ <edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
641
+ <edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
642
+ <edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
643
+ <edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
644
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
645
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
646
+ <edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
647
+ <edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
648
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
649
+ <edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
650
+ <edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
651
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
652
+ <edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
653
+ <edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
654
+ <edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
655
+ <edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
656
+ <edge from-layer="15" from-port="9" to-layer="16" to-port="1" />
657
+ <edge from-layer="15" from-port="7" to-layer="18" to-port="1" />
658
+ <edge from-layer="15" from-port="6" to-layer="18" to-port="0" />
659
+ <edge from-layer="15" from-port="11" to-layer="16" to-port="3" />
660
+ <edge from-layer="15" from-port="10" to-layer="16" to-port="2" />
661
+ <edge from-layer="15" from-port="8" to-layer="16" to-port="0" />
662
+ <edge from-layer="16" from-port="4" to-layer="18" to-port="2" />
663
+ <edge from-layer="16" from-port="5" to-layer="18" to-port="3" />
664
+ <edge from-layer="16" from-port="6" to-layer="18" to-port="4" />
665
+ <edge from-layer="16" from-port="7" to-layer="18" to-port="5" />
666
+ <edge from-layer="17" from-port="0" to-layer="18" to-port="6" />
667
+ <edge from-layer="18" from-port="11" to-layer="28" to-port="4" />
668
+ <edge from-layer="18" from-port="10" to-layer="28" to-port="3" />
669
+ <edge from-layer="18" from-port="9" to-layer="28" to-port="2" />
670
+ <edge from-layer="18" from-port="8" to-layer="28" to-port="1" />
671
+ <edge from-layer="18" from-port="7" to-layer="28" to-port="0" />
672
+ <edge from-layer="19" from-port="0" to-layer="20" to-port="0" />
673
+ <edge from-layer="20" from-port="1" to-layer="28" to-port="5" />
674
+ <edge from-layer="20" from-port="2" to-layer="28" to-port="6" />
675
+ <edge from-layer="20" from-port="3" to-layer="28" to-port="7" />
676
+ <edge from-layer="21" from-port="0" to-layer="22" to-port="0" />
677
+ <edge from-layer="22" from-port="1" to-layer="28" to-port="8" />
678
+ <edge from-layer="22" from-port="2" to-layer="28" to-port="9" />
679
+ <edge from-layer="22" from-port="3" to-layer="28" to-port="10" />
680
+ <edge from-layer="23" from-port="0" to-layer="24" to-port="0" />
681
+ <edge from-layer="24" from-port="1" to-layer="28" to-port="11" />
682
+ <edge from-layer="24" from-port="2" to-layer="28" to-port="12" />
683
+ <edge from-layer="24" from-port="3" to-layer="28" to-port="13" />
684
+ <edge from-layer="25" from-port="0" to-layer="26" to-port="0" />
685
+ <edge from-layer="26" from-port="1" to-layer="28" to-port="14" />
686
+ <edge from-layer="26" from-port="2" to-layer="28" to-port="15" />
687
+ <edge from-layer="26" from-port="3" to-layer="28" to-port="16" />
688
+ <edge from-layer="27" from-port="0" to-layer="28" to-port="17" />
689
+ <edge from-layer="28" from-port="20" to-layer="37" to-port="2" />
690
+ <edge from-layer="28" from-port="18" to-layer="29" to-port="1" />
691
+ <edge from-layer="28" from-port="18" to-layer="37" to-port="0" />
692
+ <edge from-layer="28" from-port="18" to-layer="33" to-port="1" />
693
+ <edge from-layer="28" from-port="18" to-layer="32" to-port="0" />
694
+ <edge from-layer="28" from-port="19" to-layer="29" to-port="0" />
695
+ <edge from-layer="29" from-port="2" to-layer="31" to-port="0" />
696
+ <edge from-layer="30" from-port="0" to-layer="31" to-port="1" />
697
+ <edge from-layer="31" from-port="2" to-layer="32" to-port="1" />
698
+ <edge from-layer="32" from-port="2" to-layer="33" to-port="0" />
699
+ <edge from-layer="32" from-port="2" to-layer="37" to-port="1" />
700
+ <edge from-layer="33" from-port="2" to-layer="35" to-port="0" />
701
+ <edge from-layer="34" from-port="0" to-layer="35" to-port="1" />
702
+ <edge from-layer="35" from-port="2" to-layer="37" to-port="3" />
703
+ <edge from-layer="36" from-port="0" to-layer="37" to-port="4" />
704
+ <edge from-layer="37" from-port="6" to-layer="38" to-port="0" />
705
+ <edge from-layer="37" from-port="5" to-layer="41" to-port="0" />
706
+ <edge from-layer="38" from-port="1" to-layer="39" to-port="0" />
707
+ <edge from-layer="39" from-port="1" to-layer="40" to-port="0" />
708
+ <edge from-layer="41" from-port="1" to-layer="42" to-port="0" />
709
+ </edges>
710
+ <rt_info>
711
+ <add_attention_mask value="True" />
712
+ <add_prefix_space />
713
+ <add_special_tokens value="True" />
714
+ <chat_template value="{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '&lt;|im_start|>system&#10;You are a helpful assistant.&lt;|im_end|>&#10;' }}{% endif %}{{'&lt;|im_start|>' + message['role'] + '&#10;' + message['content'] + '&lt;|im_end|>' + '&#10;'}}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|im_start|>assistant&#10;' }}{% endif %}" />
715
+ <clean_up_tokenization_spaces />
716
+ <detokenizer_input_type value="i64" />
717
+ <eos_token_id value="151645" />
718
+ <handle_special_tokens_with_re />
719
+ <number_of_inputs value="1" />
720
+ <openvino_tokenizers_version value="2024.5.0.0" />
721
+ <openvino_version value="2024.5.0" />
722
+ <original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
723
+ <pad_token_id value="151643" />
724
+ <sentencepiece_version value="0.2.0" />
725
+ <skip_special_tokens value="True" />
726
+ <streaming_detokenizer value="False" />
727
+ <tiktoken_version value="0.8.0" />
728
+ <tokenizer_output_type value="i64" />
729
+ <tokenizers_version value="0.20.3" />
730
+ <transformers_version value="4.46.3" />
731
+ <use_max_padding value="False" />
732
+ <use_sentencepiece_backend value="False" />
733
+ <utf8_replace_mode />
734
+ <with_detokenizer value="True" />
735
+ </rt_info>
736
+ </net>
openvino_vision_embeddings_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef50d0ecdf74397642e5a8f9ec608f613c1d5d7b2b6ebf070bc375af6ed1778c
3
+ size 801551128
openvino_vision_embeddings_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "LlavaProcessor",
18
+ "resample": 3,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 384,
22
+ "width": 384
23
+ }
24
+ }
processor_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "image_token": "<image>",
3
+ "patch_size": 14,
4
+ "processor_class": "LlavaProcessor",
5
+ "vision_feature_select_strategy": "default"
6
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32e8f623d8dce60b5a93496ec810434ef744287ac041cf2c6032743a3578baa5
3
+ size 11418450
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<image>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
40
+ ],
41
+ "bos_token": null,
42
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "<|im_end|>",
45
+ "errors": "replace",
46
+ "extra_special_tokens": {
47
+ "image_token": "<image>"
48
+ },
49
+ "image_token": "<image>",
50
+ "model_max_length": 32768,
51
+ "pad_token": "<|endoftext|>",
52
+ "processor_class": "LlavaProcessor",
53
+ "split_special_tokens": false,
54
+ "tokenizer_class": "Qwen2Tokenizer",
55
+ "unk_token": null
56
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff