kvaishnavi commited on
Commit
7dbf511
1 Parent(s): 33456b3

Upload Phi-3-vision-128k-instruct ONNX models

Browse files
config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Phi-3-vision-128k-instruct",
3
+ "architectures": [
4
+ "Phi3VForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_phi3_v.Phi3VConfig",
9
+ "AutoModelForCausalLM": "modeling_phi3_v.Phi3VForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "embd_layer": {
13
+ "embedding_cls": "image",
14
+ "hd_transform_order": "sub_glb",
15
+ "projection_cls": "mlp",
16
+ "use_hd_transform": true,
17
+ "with_learnable_separator": true
18
+ },
19
+ "eos_token_id": 2,
20
+ "hidden_act": "silu",
21
+ "hidden_size": 3072,
22
+ "img_processor": {
23
+ "image_dim_out": 1024,
24
+ "model_name": "openai/clip-vit-large-patch14-336",
25
+ "name": "clip_vision_model",
26
+ "num_img_tokens": 144
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 8192,
30
+ "max_position_embeddings": 131072,
31
+ "model_type": "phi3_v",
32
+ "num_attention_heads": 32,
33
+ "num_hidden_layers": 32,
34
+ "num_key_value_heads": 32,
35
+ "original_max_position_embeddings": 4096,
36
+ "rms_norm_eps": 1e-05,
37
+ "rope_scaling": {
38
+ "long_factor": [
39
+ 1.0299999713897705,
40
+ 1.0499999523162842,
41
+ 1.0499999523162842,
42
+ 1.0799999237060547,
43
+ 1.2299998998641968,
44
+ 1.2299998998641968,
45
+ 1.2999999523162842,
46
+ 1.4499999284744263,
47
+ 1.5999999046325684,
48
+ 1.6499998569488525,
49
+ 1.8999998569488525,
50
+ 2.859999895095825,
51
+ 3.68999981880188,
52
+ 5.419999599456787,
53
+ 5.489999771118164,
54
+ 5.489999771118164,
55
+ 9.09000015258789,
56
+ 11.579999923706055,
57
+ 15.65999984741211,
58
+ 15.769999504089355,
59
+ 15.789999961853027,
60
+ 18.360000610351562,
61
+ 21.989999771118164,
62
+ 23.079999923706055,
63
+ 30.009998321533203,
64
+ 32.35000228881836,
65
+ 32.590003967285156,
66
+ 35.56000518798828,
67
+ 39.95000457763672,
68
+ 53.840003967285156,
69
+ 56.20000457763672,
70
+ 57.95000457763672,
71
+ 59.29000473022461,
72
+ 59.77000427246094,
73
+ 59.920005798339844,
74
+ 61.190006256103516,
75
+ 61.96000671386719,
76
+ 62.50000762939453,
77
+ 63.3700065612793,
78
+ 63.48000717163086,
79
+ 63.48000717163086,
80
+ 63.66000747680664,
81
+ 63.850006103515625,
82
+ 64.08000946044922,
83
+ 64.760009765625,
84
+ 64.80001068115234,
85
+ 64.81001281738281,
86
+ 64.81001281738281
87
+ ],
88
+ "short_factor": [
89
+ 1.05,
90
+ 1.05,
91
+ 1.05,
92
+ 1.1,
93
+ 1.1,
94
+ 1.1,
95
+ 1.2500000000000002,
96
+ 1.2500000000000002,
97
+ 1.4000000000000004,
98
+ 1.4500000000000004,
99
+ 1.5500000000000005,
100
+ 1.8500000000000008,
101
+ 1.9000000000000008,
102
+ 2.000000000000001,
103
+ 2.000000000000001,
104
+ 2.000000000000001,
105
+ 2.000000000000001,
106
+ 2.000000000000001,
107
+ 2.000000000000001,
108
+ 2.000000000000001,
109
+ 2.000000000000001,
110
+ 2.000000000000001,
111
+ 2.000000000000001,
112
+ 2.000000000000001,
113
+ 2.000000000000001,
114
+ 2.000000000000001,
115
+ 2.000000000000001,
116
+ 2.000000000000001,
117
+ 2.000000000000001,
118
+ 2.000000000000001,
119
+ 2.000000000000001,
120
+ 2.000000000000001,
121
+ 2.1000000000000005,
122
+ 2.1000000000000005,
123
+ 2.2,
124
+ 2.3499999999999996,
125
+ 2.3499999999999996,
126
+ 2.3499999999999996,
127
+ 2.3499999999999996,
128
+ 2.3999999999999995,
129
+ 2.3999999999999995,
130
+ 2.6499999999999986,
131
+ 2.6999999999999984,
132
+ 2.8999999999999977,
133
+ 2.9499999999999975,
134
+ 3.049999999999997,
135
+ 3.049999999999997,
136
+ 3.049999999999997
137
+ ],
138
+ "type": "su"
139
+ },
140
+ "rope_theta": 10000.0,
141
+ "sliding_window": 131072,
142
+ "tie_word_embeddings": false,
143
+ "torch_dtype": "bfloat16",
144
+ "transformers_version": "4.38.1",
145
+ "use_cache": true,
146
+ "vocab_size": 32064,
147
+ "_attn_implementation": "flash_attention_2"
148
+ }
cuda-fp16/genai_config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "bos_token_id": 1,
4
+ "context_length": 131072,
5
+ "decoder": {
6
+ "session_options": {
7
+ "log_id": "onnxruntime-genai",
8
+ "provider_options": [
9
+ {
10
+ "cuda": {
11
+ "enable_cuda_graph": "0"
12
+ }
13
+ }
14
+ ]
15
+ },
16
+ "filename": "phi-3-v-128k-instruct-text.onnx",
17
+ "head_size": 96,
18
+ "hidden_size": 3072,
19
+ "inputs": {
20
+ "inputs_embeds": "inputs_embeds",
21
+ "attention_mask": "attention_mask",
22
+ "past_key_names": "past_key_values.%d.key",
23
+ "past_value_names": "past_key_values.%d.value"
24
+ },
25
+ "outputs": {
26
+ "logits": "logits",
27
+ "present_key_names": "present.%d.key",
28
+ "present_value_names": "present.%d.value"
29
+ },
30
+ "num_attention_heads": 32,
31
+ "num_hidden_layers": 32,
32
+ "num_key_value_heads": 32
33
+ },
34
+ "embedding": {
35
+ "filename": "phi-3-v-128k-instruct-text-embedding.onnx",
36
+ "inputs": {
37
+ "input_ids": "input_ids"
38
+ },
39
+ "outputs": {
40
+ "inputs_embeds": "inputs_embeds"
41
+ }
42
+ },
43
+ "vision": {
44
+ "filename": "phi-3-v-128k-instruct-vision.onnx",
45
+ "inputs": {
46
+ "pixel_values": "pixel_values",
47
+ "image_sizes": "image_sizes"
48
+ },
49
+ "outputs": {
50
+ "visual_features": "visual_features"
51
+ }
52
+ },
53
+ "eos_token_id": [
54
+ 2,
55
+ 32000,
56
+ 32001,
57
+ 32007
58
+ ],
59
+ "pad_token_id": 32000,
60
+ "type": "phi3v",
61
+ "vocab_size": 32064
62
+ },
63
+ "search": {
64
+ "diversity_penalty": 0.0,
65
+ "do_sample": false,
66
+ "early_stopping": true,
67
+ "length_penalty": 1.0,
68
+ "max_length": 131072,
69
+ "min_length": 0,
70
+ "no_repeat_ngram_size": 0,
71
+ "num_beams": 1,
72
+ "num_return_sequences": 1,
73
+ "past_present_share_buffer": true,
74
+ "repetition_penalty": 1.0,
75
+ "temperature": 1.0,
76
+ "top_k": 1,
77
+ "top_p": 1.0
78
+ }
79
+ }
cuda-fp16/phi-3-v-128k-instruct-text-embedding.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c7c1cfa5b18a03f0334b02bf774d0e069472ae110aaa786a3b2cc8f37ad15fa
3
+ size 411
cuda-fp16/phi-3-v-128k-instruct-text-embedding.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb5071dffdeee95cf3edda83cbd651f066fea4d13f537f3287d0abb4af20e1c
3
+ size 197001216
cuda-fp16/phi-3-v-128k-instruct-text.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1819aec5f7a5116d5a01491862791b1d9a23f010913afad374bc6d3e6049e0e2
3
+ size 26123076
cuda-fp16/phi-3-v-128k-instruct-text.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dc27fb464c649bcd54a533f8162b9787bc2e81920c96e1e950971261bab4b10
3
+ size 7445157888
cuda-fp16/phi-3-v-128k-instruct-vision.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccffd883fc063aa249cde4af299ac4efb292fc46b3c796b27e7c2032cef312d4
3
+ size 398735
cuda-fp16/phi-3-v-128k-instruct-vision.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91c0a60e39055b5767e557a849002ed49ee8601149a60ffb2cafd5a9e6ed122b
3
+ size 625887232
cuda-fp16/processor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "processor": {
3
+ "name": "image_processing",
4
+ "transforms": [
5
+ {
6
+ "operation": {
7
+ "name": "decode_image",
8
+ "domain": "com.microsoft.extensions",
9
+ "type": "DecodeImage",
10
+ "attrs": {
11
+ "color_space": "BGR"
12
+ }
13
+ }
14
+ },
15
+ {
16
+ "operation": {
17
+ "name": "convert_to_rgb",
18
+ "domain": "com.microsoft.extensions",
19
+ "type": "ConvertRGB"
20
+ }
21
+ },
22
+ {
23
+ "operation": {
24
+ "name": "phi3_image_transform",
25
+ "domain": "com.microsoft.extensions",
26
+ "type": "Phi3ImageTransform",
27
+ "attrs": {
28
+ "num_crops": 16,
29
+ "num_img_tokens": 144
30
+ }
31
+ }
32
+ }
33
+ ]
34
+ }
35
+ }
cuda-fp16/special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|system|>",
4
+ "<|end|>",
5
+ "<|user|>",
6
+ "<|end|>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "<|endoftext|>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "unk_token": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
cuda-fp16/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
cuda-fp16/tokenizer_config.json ADDED
@@ -0,0 +1,407 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32011": {
118
+ "content": "<|step|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": true,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32012": {
126
+ "content": "<|function_output|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": true,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "32013": {
134
+ "content": "<|tag|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": true,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "32014": {
142
+ "content": "<|function_call|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": true,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "32015": {
150
+ "content": "<|raw|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": true,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "32016": {
158
+ "content": "<|continue|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": true,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "32017": {
166
+ "content": "<|function_list|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": true,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "32018": {
174
+ "content": "<|calc|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": true,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "32019": {
182
+ "content": "<|code|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": true,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "32020": {
190
+ "content": "<|/code|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": true,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "32021": {
198
+ "content": "<|summary|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": true,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "32022": {
206
+ "content": "<|resource|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": true,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "32023": {
214
+ "content": "<|assistant_mask|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": true,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "32024": {
222
+ "content": "<|start|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": true,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "32025": {
230
+ "content": "<|message|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": true,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "32026": {
238
+ "content": "<|fim_prefix|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": true,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "32027": {
246
+ "content": "<|fim_middle|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": true,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "32028": {
254
+ "content": "<|fim_suffix|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": true,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "32029": {
262
+ "content": "<|meta_start|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": true,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "32030": {
270
+ "content": "<|ipynb_marker|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": true,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "32031": {
278
+ "content": "<|diff_marker|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": true,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "32032": {
286
+ "content": "<|ghissue|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": true,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "32033": {
294
+ "content": "<|ghreview|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": true,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "32034": {
302
+ "content": "<|disc_start|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": true,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "32035": {
310
+ "content": "<|disc_sep|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": true,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "32036": {
318
+ "content": "<|disc_thread|><|query|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": true,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "32037": {
326
+ "content": "<|/query|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": true,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "32038": {
334
+ "content": "<|data|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": true,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "32039": {
342
+ "content": "<|/data|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": true,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "32040": {
350
+ "content": "<|sys|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": true,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "32041": {
358
+ "content": "<|/sys|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": true,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "32042": {
366
+ "content": "<|inst|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": true,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "32043": {
374
+ "content": "<|/inst|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": true,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "32044": {
382
+ "content": "<|image|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": true,
386
+ "single_word": false,
387
+ "special": true
388
+ }
389
+ },
390
+ "additional_special_tokens": [
391
+ "<|system|>",
392
+ "<|end|>",
393
+ "<|user|>",
394
+ "<|end|>"
395
+ ],
396
+ "bos_token": "<s>",
397
+ "chat_template": "{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '<|assistant|>\n' -}}{% endif %}",
398
+ "clean_up_tokenization_spaces": false,
399
+ "eos_token": "<|endoftext|>",
400
+ "model_max_length": 131072,
401
+ "pad_token": "<|endoftext|>",
402
+ "padding_side": "right",
403
+ "sp_model_kwargs": {},
404
+ "tokenizer_class": "LlamaTokenizer",
405
+ "unk_token": "<unk>",
406
+ "use_default_system_prompt": false
407
+ }
cuda-int4-rtn-block-32/genai_config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "bos_token_id": 1,
4
+ "context_length": 131072,
5
+ "decoder": {
6
+ "session_options": {
7
+ "log_id": "onnxruntime-genai",
8
+ "provider_options": [
9
+ {
10
+ "cuda": {
11
+ "enable_cuda_graph": "0"
12
+ }
13
+ }
14
+ ]
15
+ },
16
+ "filename": "phi-3-v-128k-instruct-text.onnx",
17
+ "head_size": 96,
18
+ "hidden_size": 3072,
19
+ "inputs": {
20
+ "inputs_embeds": "inputs_embeds",
21
+ "attention_mask": "attention_mask",
22
+ "past_key_names": "past_key_values.%d.key",
23
+ "past_value_names": "past_key_values.%d.value"
24
+ },
25
+ "outputs": {
26
+ "logits": "logits",
27
+ "present_key_names": "present.%d.key",
28
+ "present_value_names": "present.%d.value"
29
+ },
30
+ "num_attention_heads": 32,
31
+ "num_hidden_layers": 32,
32
+ "num_key_value_heads": 32
33
+ },
34
+ "embedding": {
35
+ "filename": "phi-3-v-128k-instruct-text-embedding.onnx",
36
+ "inputs": {
37
+ "input_ids": "input_ids"
38
+ },
39
+ "outputs": {
40
+ "inputs_embeds": "inputs_embeds"
41
+ }
42
+ },
43
+ "vision": {
44
+ "filename": "phi-3-v-128k-instruct-vision.onnx",
45
+ "inputs": {
46
+ "pixel_values": "pixel_values",
47
+ "image_sizes": "image_sizes"
48
+ },
49
+ "outputs": {
50
+ "visual_features": "visual_features"
51
+ }
52
+ },
53
+ "eos_token_id": [
54
+ 2,
55
+ 32000,
56
+ 32001,
57
+ 32007
58
+ ],
59
+ "pad_token_id": 32000,
60
+ "type": "phi3v",
61
+ "vocab_size": 32064
62
+ },
63
+ "search": {
64
+ "diversity_penalty": 0.0,
65
+ "do_sample": false,
66
+ "early_stopping": true,
67
+ "length_penalty": 1.0,
68
+ "max_length": 131072,
69
+ "min_length": 0,
70
+ "no_repeat_ngram_size": 0,
71
+ "num_beams": 1,
72
+ "num_return_sequences": 1,
73
+ "past_present_share_buffer": true,
74
+ "repetition_penalty": 1.0,
75
+ "temperature": 1.0,
76
+ "top_k": 1,
77
+ "top_p": 1.0
78
+ }
79
+ }
cuda-int4-rtn-block-32/phi-3-v-128k-instruct-text-embedding.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c7c1cfa5b18a03f0334b02bf774d0e069472ae110aaa786a3b2cc8f37ad15fa
3
+ size 411
cuda-int4-rtn-block-32/phi-3-v-128k-instruct-text-embedding.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb5071dffdeee95cf3edda83cbd651f066fea4d13f537f3287d0abb4af20e1c
3
+ size 197001216
cuda-int4-rtn-block-32/phi-3-v-128k-instruct-text.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dddf37fac48112a8bd8052e3d3cddb8c7b148f805c559509db99d8ddd1b191f
3
+ size 26168928
cuda-int4-rtn-block-32/phi-3-v-128k-instruct-text.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc8568a35a27a07a0801045cbaf5feeb9a2a1c85af745600ea6345cd1c2b60c
3
+ size 2094237696
cuda-int4-rtn-block-32/phi-3-v-128k-instruct-vision.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:339fc588156547028e199b16294c95d9b8e86a7b2178de8e54bfa83f2984ece6
3
+ size 410993
cuda-int4-rtn-block-32/phi-3-v-128k-instruct-vision.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b396a234471a1eba65405344feb7115d0ff6d16905e83e6a88a52ed2d130ddc7
3
+ size 282221064
cuda-int4-rtn-block-32/processor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "processor": {
3
+ "name": "image_processing",
4
+ "transforms": [
5
+ {
6
+ "operation": {
7
+ "name": "decode_image",
8
+ "domain": "com.microsoft.extensions",
9
+ "type": "DecodeImage",
10
+ "attrs": {
11
+ "color_space": "BGR"
12
+ }
13
+ }
14
+ },
15
+ {
16
+ "operation": {
17
+ "name": "convert_to_rgb",
18
+ "domain": "com.microsoft.extensions",
19
+ "type": "ConvertRGB"
20
+ }
21
+ },
22
+ {
23
+ "operation": {
24
+ "name": "phi3_image_transform",
25
+ "domain": "com.microsoft.extensions",
26
+ "type": "Phi3ImageTransform",
27
+ "attrs": {
28
+ "num_crops": 16,
29
+ "num_img_tokens": 144
30
+ }
31
+ }
32
+ }
33
+ ]
34
+ }
35
+ }
cuda-int4-rtn-block-32/special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|system|>",
4
+ "<|end|>",
5
+ "<|user|>",
6
+ "<|end|>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "<|endoftext|>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "unk_token": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
cuda-int4-rtn-block-32/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
cuda-int4-rtn-block-32/tokenizer_config.json ADDED
@@ -0,0 +1,407 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32011": {
118
+ "content": "<|step|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": true,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32012": {
126
+ "content": "<|function_output|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": true,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "32013": {
134
+ "content": "<|tag|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": true,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "32014": {
142
+ "content": "<|function_call|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": true,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "32015": {
150
+ "content": "<|raw|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": true,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "32016": {
158
+ "content": "<|continue|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": true,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "32017": {
166
+ "content": "<|function_list|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": true,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "32018": {
174
+ "content": "<|calc|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": true,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "32019": {
182
+ "content": "<|code|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": true,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "32020": {
190
+ "content": "<|/code|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": true,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "32021": {
198
+ "content": "<|summary|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": true,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "32022": {
206
+ "content": "<|resource|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": true,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "32023": {
214
+ "content": "<|assistant_mask|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": true,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "32024": {
222
+ "content": "<|start|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": true,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "32025": {
230
+ "content": "<|message|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": true,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "32026": {
238
+ "content": "<|fim_prefix|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": true,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "32027": {
246
+ "content": "<|fim_middle|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": true,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "32028": {
254
+ "content": "<|fim_suffix|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": true,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "32029": {
262
+ "content": "<|meta_start|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": true,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "32030": {
270
+ "content": "<|ipynb_marker|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": true,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "32031": {
278
+ "content": "<|diff_marker|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": true,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "32032": {
286
+ "content": "<|ghissue|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": true,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "32033": {
294
+ "content": "<|ghreview|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": true,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "32034": {
302
+ "content": "<|disc_start|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": true,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "32035": {
310
+ "content": "<|disc_sep|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": true,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "32036": {
318
+ "content": "<|disc_thread|><|query|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": true,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "32037": {
326
+ "content": "<|/query|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": true,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "32038": {
334
+ "content": "<|data|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": true,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "32039": {
342
+ "content": "<|/data|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": true,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "32040": {
350
+ "content": "<|sys|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": true,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "32041": {
358
+ "content": "<|/sys|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": true,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "32042": {
366
+ "content": "<|inst|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": true,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "32043": {
374
+ "content": "<|/inst|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": true,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "32044": {
382
+ "content": "<|image|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": true,
386
+ "single_word": false,
387
+ "special": true
388
+ }
389
+ },
390
+ "additional_special_tokens": [
391
+ "<|system|>",
392
+ "<|end|>",
393
+ "<|user|>",
394
+ "<|end|>"
395
+ ],
396
+ "bos_token": "<s>",
397
+ "chat_template": "{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '<|assistant|>\n' -}}{% endif %}",
398
+ "clean_up_tokenization_spaces": false,
399
+ "eos_token": "<|endoftext|>",
400
+ "model_max_length": 131072,
401
+ "pad_token": "<|endoftext|>",
402
+ "padding_side": "right",
403
+ "sp_model_kwargs": {},
404
+ "tokenizer_class": "LlamaTokenizer",
405
+ "unk_token": "<unk>",
406
+ "use_default_system_prompt": false
407
+ }