goodspeed3 commited on
Commit
006b8d1
β€’
1 Parent(s): 02501b3

structure for tf.js

Browse files
Files changed (40) hide show
  1. cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/added_tokens.json β†’ added_tokens.json +0 -0
  2. cpu_and_mobile/cpu-int4-rtn-block-32/added_tokens.json +0 -40
  3. cpu_and_mobile/cpu-int4-rtn-block-32/genai_config.json +0 -53
  4. cpu_and_mobile/cpu-int4-rtn-block-32/phi3-mini-128k-instruct-cpu-int4-rtn-block-32.onnx +0 -3
  5. cpu_and_mobile/cpu-int4-rtn-block-32/phi3-mini-128k-instruct-cpu-int4-rtn-block-32.onnx.data +0 -3
  6. cpu_and_mobile/cpu-int4-rtn-block-32/special_tokens_map.json +0 -33
  7. cpu_and_mobile/cpu-int4-rtn-block-32/tokenizer.json +0 -0
  8. cpu_and_mobile/cpu-int4-rtn-block-32/tokenizer.model +0 -3
  9. cpu_and_mobile/cpu-int4-rtn-block-32/tokenizer_config.json +0 -349
  10. cuda/cuda-fp16/added_tokens.json +0 -40
  11. cuda/cuda-fp16/genai_config.json +0 -58
  12. cuda/cuda-fp16/phi3-mini-128k-instruct-cuda-fp16.onnx +0 -3
  13. cuda/cuda-fp16/phi3-mini-128k-instruct-cuda-fp16.onnx.data +0 -3
  14. cuda/cuda-fp16/special_tokens_map.json +0 -33
  15. cuda/cuda-fp16/tokenizer.json +0 -0
  16. cuda/cuda-fp16/tokenizer.model +0 -3
  17. cuda/cuda-fp16/tokenizer_config.json +0 -349
  18. cuda/cuda-int4-rtn-block-32/added_tokens.json +0 -40
  19. cuda/cuda-int4-rtn-block-32/genai_config.json +0 -58
  20. cuda/cuda-int4-rtn-block-32/phi3-mini-128k-instruct-cuda-int4-rtn-block-32.onnx +0 -3
  21. cuda/cuda-int4-rtn-block-32/phi3-mini-128k-instruct-cuda-int4-rtn-block-32.onnx.data +0 -3
  22. cuda/cuda-int4-rtn-block-32/special_tokens_map.json +0 -33
  23. cuda/cuda-int4-rtn-block-32/tokenizer.json +0 -0
  24. cuda/cuda-int4-rtn-block-32/tokenizer.model +0 -3
  25. cuda/cuda-int4-rtn-block-32/tokenizer_config.json +0 -349
  26. directml/directml-int4-awq-block-128/added_tokens.json +0 -40
  27. directml/directml-int4-awq-block-128/genai_config.json +0 -56
  28. directml/directml-int4-awq-block-128/model.onnx +0 -3
  29. directml/directml-int4-awq-block-128/model.onnx.data +0 -3
  30. directml/directml-int4-awq-block-128/special_tokens_map.json +0 -33
  31. directml/directml-int4-awq-block-128/tokenizer.json +0 -0
  32. directml/directml-int4-awq-block-128/tokenizer.model +0 -3
  33. directml/directml-int4-awq-block-128/tokenizer_config.json +0 -349
  34. cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/genai_config.json β†’ genai_config.json +0 -0
  35. cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi3-mini-128k-instruct-cpu-int4-rtn-block-32-acc-level-4.onnx β†’ onnx/decoder_model_merged_quantized.onnx +0 -0
  36. cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi3-mini-128k-instruct-cpu-int4-rtn-block-32-acc-level-4.onnx.data β†’ onnx/decoder_model_merged_quantized.onnx.data +0 -0
  37. cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/special_tokens_map.json β†’ special_tokens_map.json +0 -0
  38. cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer.json β†’ tokenizer.json +0 -0
  39. cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer.model β†’ tokenizer.model +0 -0
  40. cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer_config.json β†’ tokenizer_config.json +0 -0
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/added_tokens.json β†’ added_tokens.json RENAMED
File without changes
cpu_and_mobile/cpu-int4-rtn-block-32/added_tokens.json DELETED
@@ -1,40 +0,0 @@
1
- {
2
- "<|/code|>": 32014,
3
- "<|/data|>": 32033,
4
- "<|/inst|>": 32037,
5
- "<|/query|>": 32031,
6
- "<|/sys|>": 32035,
7
- "<|assistant_mask|>": 32017,
8
- "<|assistant|>": 32001,
9
- "<|calc|>": 32012,
10
- "<|code|>": 32013,
11
- "<|continue|>": 32009,
12
- "<|data|>": 32032,
13
- "<|diff_marker|>": 32025,
14
- "<|disc_sep|>": 32029,
15
- "<|disc_start|>": 32028,
16
- "<|disc_thread|><|query|>": 32030,
17
- "<|endoftext|>": 32000,
18
- "<|end|>": 32007,
19
- "<|fim_middle|>": 32021,
20
- "<|fim_prefix|>": 32020,
21
- "<|fim_suffix|>": 32022,
22
- "<|function_call|>": 32005,
23
- "<|function_list|>": 32011,
24
- "<|function_output|>": 32003,
25
- "<|ghissue|>": 32026,
26
- "<|ghreview|>": 32027,
27
- "<|inst|>": 32036,
28
- "<|ipynb_marker|>": 32024,
29
- "<|message|>": 32019,
30
- "<|meta_start|>": 32023,
31
- "<|raw|>": 32008,
32
- "<|resource|>": 32016,
33
- "<|start|>": 32018,
34
- "<|step|>": 32002,
35
- "<|summary|>": 32015,
36
- "<|system|>": 32006,
37
- "<|sys|>": 32034,
38
- "<|tag|>": 32004,
39
- "<|user|>": 32010
40
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cpu_and_mobile/cpu-int4-rtn-block-32/genai_config.json DELETED
@@ -1,53 +0,0 @@
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
- "filename": "phi3-mini-128k-instruct-cpu-int4-rtn-block-32.onnx",
11
- "head_size": 96,
12
- "hidden_size": 3072,
13
- "inputs": {
14
- "input_ids": "input_ids",
15
- "attention_mask": "attention_mask",
16
- "position_ids": "position_ids",
17
- "past_key_names": "past_key_values.%d.key",
18
- "past_value_names": "past_key_values.%d.value"
19
- },
20
- "outputs": {
21
- "logits": "logits",
22
- "present_key_names": "present.%d.key",
23
- "present_value_names": "present.%d.value"
24
- },
25
- "num_attention_heads": 32,
26
- "num_hidden_layers": 32,
27
- "num_key_value_heads": 32
28
- },
29
- "eos_token_id": [
30
- 32000,
31
- 32007
32
- ],
33
- "pad_token_id": 32000,
34
- "type": "phi3",
35
- "vocab_size": 32064
36
- },
37
- "search": {
38
- "diversity_penalty": 0.0,
39
- "do_sample": false,
40
- "early_stopping": true,
41
- "length_penalty": 1.0,
42
- "max_length": 131072,
43
- "min_length": 0,
44
- "no_repeat_ngram_size": 0,
45
- "num_beams": 1,
46
- "num_return_sequences": 1,
47
- "past_present_share_buffer": false,
48
- "repetition_penalty": 1.0,
49
- "temperature": 1.0,
50
- "top_k": 1,
51
- "top_p": 1.0
52
- }
53
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cpu_and_mobile/cpu-int4-rtn-block-32/phi3-mini-128k-instruct-cpu-int4-rtn-block-32.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbcb209993e7508380321a5b57f33c24c5c20ae3f9d22f6cc6b51c5f4bdab79a
3
- size 52219716
 
 
 
 
cpu_and_mobile/cpu-int4-rtn-block-32/phi3-mini-128k-instruct-cpu-int4-rtn-block-32.onnx.data DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:96f994210878f40a67cb1690e8ff3a94653d84f18886ca7c8ba9c6fc3eec1cd9
3
- size 2721288192
 
 
 
 
cpu_and_mobile/cpu-int4-rtn-block-32/special_tokens_map.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|/inst|>"
4
- ],
5
- "bos_token": {
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "eos_token": {
13
- "content": "<|endoftext|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "pad_token": {
20
- "content": "<|endoftext|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cpu_and_mobile/cpu-int4-rtn-block-32/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
cpu_and_mobile/cpu-int4-rtn-block-32/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
 
 
 
cpu_and_mobile/cpu-int4-rtn-block-32/tokenizer_config.json DELETED
@@ -1,349 +0,0 @@
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": "<|step|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": true,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "32003": {
54
- "content": "<|function_output|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": true,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "32004": {
62
- "content": "<|tag|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": true,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "32005": {
70
- "content": "<|function_call|>",
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": true,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "32007": {
86
- "content": "<|end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": true,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "32008": {
94
- "content": "<|raw|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": true,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "32009": {
102
- "content": "<|continue|>",
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": true,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "32011": {
118
- "content": "<|function_list|>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": true,
122
- "single_word": false,
123
- "special": true
124
- },
125
- "32012": {
126
- "content": "<|calc|>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": true,
130
- "single_word": false,
131
- "special": true
132
- },
133
- "32013": {
134
- "content": "<|code|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": true,
138
- "single_word": false,
139
- "special": true
140
- },
141
- "32014": {
142
- "content": "<|/code|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": true,
146
- "single_word": false,
147
- "special": true
148
- },
149
- "32015": {
150
- "content": "<|summary|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": true,
154
- "single_word": false,
155
- "special": true
156
- },
157
- "32016": {
158
- "content": "<|resource|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": true,
162
- "single_word": false,
163
- "special": true
164
- },
165
- "32017": {
166
- "content": "<|assistant_mask|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": true,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "32018": {
174
- "content": "<|start|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": true,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "32019": {
182
- "content": "<|message|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": true,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "32020": {
190
- "content": "<|fim_prefix|>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": true,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "32021": {
198
- "content": "<|fim_middle|>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": true,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "32022": {
206
- "content": "<|fim_suffix|>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": true,
210
- "single_word": false,
211
- "special": true
212
- },
213
- "32023": {
214
- "content": "<|meta_start|>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": true,
218
- "single_word": false,
219
- "special": true
220
- },
221
- "32024": {
222
- "content": "<|ipynb_marker|>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": true,
226
- "single_word": false,
227
- "special": true
228
- },
229
- "32025": {
230
- "content": "<|diff_marker|>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": true,
234
- "single_word": false,
235
- "special": true
236
- },
237
- "32026": {
238
- "content": "<|ghissue|>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": true,
242
- "single_word": false,
243
- "special": true
244
- },
245
- "32027": {
246
- "content": "<|ghreview|>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": true,
250
- "single_word": false,
251
- "special": true
252
- },
253
- "32028": {
254
- "content": "<|disc_start|>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": true,
258
- "single_word": false,
259
- "special": true
260
- },
261
- "32029": {
262
- "content": "<|disc_sep|>",
263
- "lstrip": false,
264
- "normalized": false,
265
- "rstrip": true,
266
- "single_word": false,
267
- "special": true
268
- },
269
- "32030": {
270
- "content": "<|disc_thread|><|query|>",
271
- "lstrip": false,
272
- "normalized": false,
273
- "rstrip": true,
274
- "single_word": false,
275
- "special": true
276
- },
277
- "32031": {
278
- "content": "<|/query|>",
279
- "lstrip": false,
280
- "normalized": false,
281
- "rstrip": true,
282
- "single_word": false,
283
- "special": true
284
- },
285
- "32032": {
286
- "content": "<|data|>",
287
- "lstrip": false,
288
- "normalized": false,
289
- "rstrip": true,
290
- "single_word": false,
291
- "special": true
292
- },
293
- "32033": {
294
- "content": "<|/data|>",
295
- "lstrip": false,
296
- "normalized": false,
297
- "rstrip": true,
298
- "single_word": false,
299
- "special": true
300
- },
301
- "32034": {
302
- "content": "<|sys|>",
303
- "lstrip": false,
304
- "normalized": false,
305
- "rstrip": true,
306
- "single_word": false,
307
- "special": true
308
- },
309
- "32035": {
310
- "content": "<|/sys|>",
311
- "lstrip": false,
312
- "normalized": false,
313
- "rstrip": true,
314
- "single_word": false,
315
- "special": true
316
- },
317
- "32036": {
318
- "content": "<|inst|>",
319
- "lstrip": false,
320
- "normalized": false,
321
- "rstrip": true,
322
- "single_word": false,
323
- "special": true
324
- },
325
- "32037": {
326
- "content": "<|/inst|>",
327
- "lstrip": false,
328
- "normalized": false,
329
- "rstrip": true,
330
- "single_word": false,
331
- "special": true
332
- }
333
- },
334
- "additional_special_tokens": [
335
- "<|/inst|>"
336
- ],
337
- "bos_token": "<s>",
338
- "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
339
- "clean_up_tokenization_spaces": false,
340
- "eos_token": "<|endoftext|>",
341
- "legacy": false,
342
- "model_max_length": 131072,
343
- "pad_token": "<|endoftext|>",
344
- "padding_side": "left",
345
- "sp_model_kwargs": {},
346
- "tokenizer_class": "LlamaTokenizer",
347
- "unk_token": "<unk>",
348
- "use_default_system_prompt": false
349
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cuda/cuda-fp16/added_tokens.json DELETED
@@ -1,40 +0,0 @@
1
- {
2
- "<|/code|>": 32014,
3
- "<|/data|>": 32033,
4
- "<|/inst|>": 32037,
5
- "<|/query|>": 32031,
6
- "<|/sys|>": 32035,
7
- "<|assistant_mask|>": 32017,
8
- "<|assistant|>": 32001,
9
- "<|calc|>": 32012,
10
- "<|code|>": 32013,
11
- "<|continue|>": 32009,
12
- "<|data|>": 32032,
13
- "<|diff_marker|>": 32025,
14
- "<|disc_sep|>": 32029,
15
- "<|disc_start|>": 32028,
16
- "<|disc_thread|><|query|>": 32030,
17
- "<|endoftext|>": 32000,
18
- "<|end|>": 32007,
19
- "<|fim_middle|>": 32021,
20
- "<|fim_prefix|>": 32020,
21
- "<|fim_suffix|>": 32022,
22
- "<|function_call|>": 32005,
23
- "<|function_list|>": 32011,
24
- "<|function_output|>": 32003,
25
- "<|ghissue|>": 32026,
26
- "<|ghreview|>": 32027,
27
- "<|inst|>": 32036,
28
- "<|ipynb_marker|>": 32024,
29
- "<|message|>": 32019,
30
- "<|meta_start|>": 32023,
31
- "<|raw|>": 32008,
32
- "<|resource|>": 32016,
33
- "<|start|>": 32018,
34
- "<|step|>": 32002,
35
- "<|summary|>": 32015,
36
- "<|system|>": 32006,
37
- "<|sys|>": 32034,
38
- "<|tag|>": 32004,
39
- "<|user|>": 32010
40
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cuda/cuda-fp16/genai_config.json DELETED
@@ -1,58 +0,0 @@
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": "phi3-mini-128k-instruct-cuda-fp16.onnx",
17
- "head_size": 96,
18
- "hidden_size": 3072,
19
- "inputs": {
20
- "input_ids": "input_ids",
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
- "eos_token_id": [
35
- 32000,
36
- 32007
37
- ],
38
- "pad_token_id": 32000,
39
- "type": "phi3",
40
- "vocab_size": 32064
41
- },
42
- "search": {
43
- "diversity_penalty": 0.0,
44
- "do_sample": false,
45
- "early_stopping": true,
46
- "length_penalty": 1.0,
47
- "max_length": 131072,
48
- "min_length": 0,
49
- "no_repeat_ngram_size": 0,
50
- "num_beams": 1,
51
- "num_return_sequences": 1,
52
- "past_present_share_buffer": true,
53
- "repetition_penalty": 1.0,
54
- "temperature": 1.0,
55
- "top_k": 1,
56
- "top_p": 1.0
57
- }
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cuda/cuda-fp16/phi3-mini-128k-instruct-cuda-fp16.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:543dbe021574541134fdd975a9c22b80c38ca3d8ec7138db937fdd93b0914a99
3
- size 26125048
 
 
 
 
cuda/cuda-fp16/phi3-mini-128k-instruct-cuda-fp16.onnx.data DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7646ea1bb3523183c07fde0814980a4d0aa488abf4e6364979d67ea19939e245
3
- size 7642159104
 
 
 
 
cuda/cuda-fp16/special_tokens_map.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|/inst|>"
4
- ],
5
- "bos_token": {
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "eos_token": {
13
- "content": "<|endoftext|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "pad_token": {
20
- "content": "<|endoftext|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cuda/cuda-fp16/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
cuda/cuda-fp16/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
 
 
 
cuda/cuda-fp16/tokenizer_config.json DELETED
@@ -1,349 +0,0 @@
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": "<|step|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": true,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "32003": {
54
- "content": "<|function_output|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": true,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "32004": {
62
- "content": "<|tag|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": true,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "32005": {
70
- "content": "<|function_call|>",
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": true,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "32007": {
86
- "content": "<|end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": true,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "32008": {
94
- "content": "<|raw|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": true,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "32009": {
102
- "content": "<|continue|>",
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": true,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "32011": {
118
- "content": "<|function_list|>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": true,
122
- "single_word": false,
123
- "special": true
124
- },
125
- "32012": {
126
- "content": "<|calc|>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": true,
130
- "single_word": false,
131
- "special": true
132
- },
133
- "32013": {
134
- "content": "<|code|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": true,
138
- "single_word": false,
139
- "special": true
140
- },
141
- "32014": {
142
- "content": "<|/code|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": true,
146
- "single_word": false,
147
- "special": true
148
- },
149
- "32015": {
150
- "content": "<|summary|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": true,
154
- "single_word": false,
155
- "special": true
156
- },
157
- "32016": {
158
- "content": "<|resource|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": true,
162
- "single_word": false,
163
- "special": true
164
- },
165
- "32017": {
166
- "content": "<|assistant_mask|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": true,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "32018": {
174
- "content": "<|start|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": true,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "32019": {
182
- "content": "<|message|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": true,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "32020": {
190
- "content": "<|fim_prefix|>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": true,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "32021": {
198
- "content": "<|fim_middle|>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": true,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "32022": {
206
- "content": "<|fim_suffix|>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": true,
210
- "single_word": false,
211
- "special": true
212
- },
213
- "32023": {
214
- "content": "<|meta_start|>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": true,
218
- "single_word": false,
219
- "special": true
220
- },
221
- "32024": {
222
- "content": "<|ipynb_marker|>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": true,
226
- "single_word": false,
227
- "special": true
228
- },
229
- "32025": {
230
- "content": "<|diff_marker|>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": true,
234
- "single_word": false,
235
- "special": true
236
- },
237
- "32026": {
238
- "content": "<|ghissue|>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": true,
242
- "single_word": false,
243
- "special": true
244
- },
245
- "32027": {
246
- "content": "<|ghreview|>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": true,
250
- "single_word": false,
251
- "special": true
252
- },
253
- "32028": {
254
- "content": "<|disc_start|>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": true,
258
- "single_word": false,
259
- "special": true
260
- },
261
- "32029": {
262
- "content": "<|disc_sep|>",
263
- "lstrip": false,
264
- "normalized": false,
265
- "rstrip": true,
266
- "single_word": false,
267
- "special": true
268
- },
269
- "32030": {
270
- "content": "<|disc_thread|><|query|>",
271
- "lstrip": false,
272
- "normalized": false,
273
- "rstrip": true,
274
- "single_word": false,
275
- "special": true
276
- },
277
- "32031": {
278
- "content": "<|/query|>",
279
- "lstrip": false,
280
- "normalized": false,
281
- "rstrip": true,
282
- "single_word": false,
283
- "special": true
284
- },
285
- "32032": {
286
- "content": "<|data|>",
287
- "lstrip": false,
288
- "normalized": false,
289
- "rstrip": true,
290
- "single_word": false,
291
- "special": true
292
- },
293
- "32033": {
294
- "content": "<|/data|>",
295
- "lstrip": false,
296
- "normalized": false,
297
- "rstrip": true,
298
- "single_word": false,
299
- "special": true
300
- },
301
- "32034": {
302
- "content": "<|sys|>",
303
- "lstrip": false,
304
- "normalized": false,
305
- "rstrip": true,
306
- "single_word": false,
307
- "special": true
308
- },
309
- "32035": {
310
- "content": "<|/sys|>",
311
- "lstrip": false,
312
- "normalized": false,
313
- "rstrip": true,
314
- "single_word": false,
315
- "special": true
316
- },
317
- "32036": {
318
- "content": "<|inst|>",
319
- "lstrip": false,
320
- "normalized": false,
321
- "rstrip": true,
322
- "single_word": false,
323
- "special": true
324
- },
325
- "32037": {
326
- "content": "<|/inst|>",
327
- "lstrip": false,
328
- "normalized": false,
329
- "rstrip": true,
330
- "single_word": false,
331
- "special": true
332
- }
333
- },
334
- "additional_special_tokens": [
335
- "<|/inst|>"
336
- ],
337
- "bos_token": "<s>",
338
- "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
339
- "clean_up_tokenization_spaces": false,
340
- "eos_token": "<|endoftext|>",
341
- "legacy": false,
342
- "model_max_length": 131072,
343
- "pad_token": "<|endoftext|>",
344
- "padding_side": "left",
345
- "sp_model_kwargs": {},
346
- "tokenizer_class": "LlamaTokenizer",
347
- "unk_token": "<unk>",
348
- "use_default_system_prompt": false
349
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cuda/cuda-int4-rtn-block-32/added_tokens.json DELETED
@@ -1,40 +0,0 @@
1
- {
2
- "<|/code|>": 32014,
3
- "<|/data|>": 32033,
4
- "<|/inst|>": 32037,
5
- "<|/query|>": 32031,
6
- "<|/sys|>": 32035,
7
- "<|assistant_mask|>": 32017,
8
- "<|assistant|>": 32001,
9
- "<|calc|>": 32012,
10
- "<|code|>": 32013,
11
- "<|continue|>": 32009,
12
- "<|data|>": 32032,
13
- "<|diff_marker|>": 32025,
14
- "<|disc_sep|>": 32029,
15
- "<|disc_start|>": 32028,
16
- "<|disc_thread|><|query|>": 32030,
17
- "<|endoftext|>": 32000,
18
- "<|end|>": 32007,
19
- "<|fim_middle|>": 32021,
20
- "<|fim_prefix|>": 32020,
21
- "<|fim_suffix|>": 32022,
22
- "<|function_call|>": 32005,
23
- "<|function_list|>": 32011,
24
- "<|function_output|>": 32003,
25
- "<|ghissue|>": 32026,
26
- "<|ghreview|>": 32027,
27
- "<|inst|>": 32036,
28
- "<|ipynb_marker|>": 32024,
29
- "<|message|>": 32019,
30
- "<|meta_start|>": 32023,
31
- "<|raw|>": 32008,
32
- "<|resource|>": 32016,
33
- "<|start|>": 32018,
34
- "<|step|>": 32002,
35
- "<|summary|>": 32015,
36
- "<|system|>": 32006,
37
- "<|sys|>": 32034,
38
- "<|tag|>": 32004,
39
- "<|user|>": 32010
40
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cuda/cuda-int4-rtn-block-32/genai_config.json DELETED
@@ -1,58 +0,0 @@
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": "phi3-mini-128k-instruct-cuda-int4-rtn-block-32.onnx",
17
- "head_size": 96,
18
- "hidden_size": 3072,
19
- "inputs": {
20
- "input_ids": "input_ids",
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
- "eos_token_id": [
35
- 32000,
36
- 32007
37
- ],
38
- "pad_token_id": 32000,
39
- "type": "phi3",
40
- "vocab_size": 32064
41
- },
42
- "search": {
43
- "diversity_penalty": 0.0,
44
- "do_sample": false,
45
- "early_stopping": true,
46
- "length_penalty": 1.0,
47
- "max_length": 131072,
48
- "min_length": 0,
49
- "no_repeat_ngram_size": 0,
50
- "num_beams": 1,
51
- "num_return_sequences": 1,
52
- "past_present_share_buffer": true,
53
- "repetition_penalty": 1.0,
54
- "temperature": 1.0,
55
- "top_k": 1,
56
- "top_p": 1.0
57
- }
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cuda/cuda-int4-rtn-block-32/phi3-mini-128k-instruct-cuda-int4-rtn-block-32.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:89ecae6d6e74c4d15bdf6dad8fa11c4f56f79328cd1623d336bae52693538e75
3
- size 26177313
 
 
 
 
cuda/cuda-int4-rtn-block-32/phi3-mini-128k-instruct-cuda-int4-rtn-block-32.onnx.data DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c7117fdc3bc7a4a15146523809528f6ccd62202a117d0edde8c2f6c158c45d3
3
- size 2291238912
 
 
 
 
cuda/cuda-int4-rtn-block-32/special_tokens_map.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|/inst|>"
4
- ],
5
- "bos_token": {
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "eos_token": {
13
- "content": "<|endoftext|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "pad_token": {
20
- "content": "<|endoftext|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cuda/cuda-int4-rtn-block-32/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
cuda/cuda-int4-rtn-block-32/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
 
 
 
cuda/cuda-int4-rtn-block-32/tokenizer_config.json DELETED
@@ -1,349 +0,0 @@
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": "<|step|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": true,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "32003": {
54
- "content": "<|function_output|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": true,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "32004": {
62
- "content": "<|tag|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": true,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "32005": {
70
- "content": "<|function_call|>",
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": true,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "32007": {
86
- "content": "<|end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": true,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "32008": {
94
- "content": "<|raw|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": true,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "32009": {
102
- "content": "<|continue|>",
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": true,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "32011": {
118
- "content": "<|function_list|>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": true,
122
- "single_word": false,
123
- "special": true
124
- },
125
- "32012": {
126
- "content": "<|calc|>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": true,
130
- "single_word": false,
131
- "special": true
132
- },
133
- "32013": {
134
- "content": "<|code|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": true,
138
- "single_word": false,
139
- "special": true
140
- },
141
- "32014": {
142
- "content": "<|/code|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": true,
146
- "single_word": false,
147
- "special": true
148
- },
149
- "32015": {
150
- "content": "<|summary|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": true,
154
- "single_word": false,
155
- "special": true
156
- },
157
- "32016": {
158
- "content": "<|resource|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": true,
162
- "single_word": false,
163
- "special": true
164
- },
165
- "32017": {
166
- "content": "<|assistant_mask|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": true,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "32018": {
174
- "content": "<|start|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": true,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "32019": {
182
- "content": "<|message|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": true,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "32020": {
190
- "content": "<|fim_prefix|>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": true,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "32021": {
198
- "content": "<|fim_middle|>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": true,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "32022": {
206
- "content": "<|fim_suffix|>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": true,
210
- "single_word": false,
211
- "special": true
212
- },
213
- "32023": {
214
- "content": "<|meta_start|>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": true,
218
- "single_word": false,
219
- "special": true
220
- },
221
- "32024": {
222
- "content": "<|ipynb_marker|>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": true,
226
- "single_word": false,
227
- "special": true
228
- },
229
- "32025": {
230
- "content": "<|diff_marker|>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": true,
234
- "single_word": false,
235
- "special": true
236
- },
237
- "32026": {
238
- "content": "<|ghissue|>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": true,
242
- "single_word": false,
243
- "special": true
244
- },
245
- "32027": {
246
- "content": "<|ghreview|>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": true,
250
- "single_word": false,
251
- "special": true
252
- },
253
- "32028": {
254
- "content": "<|disc_start|>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": true,
258
- "single_word": false,
259
- "special": true
260
- },
261
- "32029": {
262
- "content": "<|disc_sep|>",
263
- "lstrip": false,
264
- "normalized": false,
265
- "rstrip": true,
266
- "single_word": false,
267
- "special": true
268
- },
269
- "32030": {
270
- "content": "<|disc_thread|><|query|>",
271
- "lstrip": false,
272
- "normalized": false,
273
- "rstrip": true,
274
- "single_word": false,
275
- "special": true
276
- },
277
- "32031": {
278
- "content": "<|/query|>",
279
- "lstrip": false,
280
- "normalized": false,
281
- "rstrip": true,
282
- "single_word": false,
283
- "special": true
284
- },
285
- "32032": {
286
- "content": "<|data|>",
287
- "lstrip": false,
288
- "normalized": false,
289
- "rstrip": true,
290
- "single_word": false,
291
- "special": true
292
- },
293
- "32033": {
294
- "content": "<|/data|>",
295
- "lstrip": false,
296
- "normalized": false,
297
- "rstrip": true,
298
- "single_word": false,
299
- "special": true
300
- },
301
- "32034": {
302
- "content": "<|sys|>",
303
- "lstrip": false,
304
- "normalized": false,
305
- "rstrip": true,
306
- "single_word": false,
307
- "special": true
308
- },
309
- "32035": {
310
- "content": "<|/sys|>",
311
- "lstrip": false,
312
- "normalized": false,
313
- "rstrip": true,
314
- "single_word": false,
315
- "special": true
316
- },
317
- "32036": {
318
- "content": "<|inst|>",
319
- "lstrip": false,
320
- "normalized": false,
321
- "rstrip": true,
322
- "single_word": false,
323
- "special": true
324
- },
325
- "32037": {
326
- "content": "<|/inst|>",
327
- "lstrip": false,
328
- "normalized": false,
329
- "rstrip": true,
330
- "single_word": false,
331
- "special": true
332
- }
333
- },
334
- "additional_special_tokens": [
335
- "<|/inst|>"
336
- ],
337
- "bos_token": "<s>",
338
- "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
339
- "clean_up_tokenization_spaces": false,
340
- "eos_token": "<|endoftext|>",
341
- "legacy": false,
342
- "model_max_length": 131072,
343
- "pad_token": "<|endoftext|>",
344
- "padding_side": "left",
345
- "sp_model_kwargs": {},
346
- "tokenizer_class": "LlamaTokenizer",
347
- "unk_token": "<unk>",
348
- "use_default_system_prompt": false
349
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
directml/directml-int4-awq-block-128/added_tokens.json DELETED
@@ -1,40 +0,0 @@
1
- {
2
- "<|/code|>": 32014,
3
- "<|/data|>": 32033,
4
- "<|/inst|>": 32037,
5
- "<|/query|>": 32031,
6
- "<|/sys|>": 32035,
7
- "<|assistant_mask|>": 32017,
8
- "<|assistant|>": 32001,
9
- "<|calc|>": 32012,
10
- "<|code|>": 32013,
11
- "<|continue|>": 32009,
12
- "<|data|>": 32032,
13
- "<|diff_marker|>": 32025,
14
- "<|disc_sep|>": 32029,
15
- "<|disc_start|>": 32028,
16
- "<|disc_thread|><|query|>": 32030,
17
- "<|endoftext|>": 32000,
18
- "<|end|>": 32007,
19
- "<|fim_middle|>": 32021,
20
- "<|fim_prefix|>": 32020,
21
- "<|fim_suffix|>": 32022,
22
- "<|function_call|>": 32005,
23
- "<|function_list|>": 32011,
24
- "<|function_output|>": 32003,
25
- "<|ghissue|>": 32026,
26
- "<|ghreview|>": 32027,
27
- "<|inst|>": 32036,
28
- "<|ipynb_marker|>": 32024,
29
- "<|message|>": 32019,
30
- "<|meta_start|>": 32023,
31
- "<|raw|>": 32008,
32
- "<|resource|>": 32016,
33
- "<|start|>": 32018,
34
- "<|step|>": 32002,
35
- "<|summary|>": 32015,
36
- "<|system|>": 32006,
37
- "<|sys|>": 32034,
38
- "<|tag|>": 32004,
39
- "<|user|>": 32010
40
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
directml/directml-int4-awq-block-128/genai_config.json DELETED
@@ -1,56 +0,0 @@
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
- "dml": {}
11
- }
12
- ]
13
- },
14
- "filename": "model.onnx",
15
- "head_size": 96,
16
- "hidden_size": 3072,
17
- "inputs": {
18
- "input_ids": "input_ids",
19
- "attention_mask": "attention_mask",
20
- "past_key_names": "past_key_values.%d.key",
21
- "past_value_names": "past_key_values.%d.value"
22
- },
23
- "outputs": {
24
- "logits": "logits",
25
- "present_key_names": "present.%d.key",
26
- "present_value_names": "present.%d.value"
27
- },
28
- "num_attention_heads": 32,
29
- "num_hidden_layers": 32,
30
- "num_key_value_heads": 32
31
- },
32
- "eos_token_id": [
33
- 32000,
34
- 32007
35
- ],
36
- "pad_token_id": 32000,
37
- "type": "phi3",
38
- "vocab_size": 32064
39
- },
40
- "search": {
41
- "diversity_penalty": 0.0,
42
- "do_sample": false,
43
- "early_stopping": true,
44
- "length_penalty": 1.0,
45
- "max_length": 131072,
46
- "min_length": 0,
47
- "no_repeat_ngram_size": 0,
48
- "num_beams": 1,
49
- "num_return_sequences": 1,
50
- "past_present_share_buffer": true,
51
- "repetition_penalty": 1.0,
52
- "temperature": 1.0,
53
- "top_k": 1,
54
- "top_p": 1.0
55
- }
56
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
directml/directml-int4-awq-block-128/model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:eac80c41ab030386a8074bb04a43f05a1572b4efaf7fca3a3d3bafd1b4aaeeb7
3
- size 32594397
 
 
 
 
directml/directml-int4-awq-block-128/model.onnx.data DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e19d903f9f384ba6199c8285722b9cb8a9a27a3657d69b963891d35fab459e11
3
- size 2131292928
 
 
 
 
directml/directml-int4-awq-block-128/special_tokens_map.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|/inst|>"
4
- ],
5
- "bos_token": {
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "eos_token": {
13
- "content": "<|endoftext|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "pad_token": {
20
- "content": "<|endoftext|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
directml/directml-int4-awq-block-128/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
directml/directml-int4-awq-block-128/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
 
 
 
directml/directml-int4-awq-block-128/tokenizer_config.json DELETED
@@ -1,349 +0,0 @@
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": "<|step|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": true,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "32003": {
54
- "content": "<|function_output|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": true,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "32004": {
62
- "content": "<|tag|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": true,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "32005": {
70
- "content": "<|function_call|>",
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": true,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "32007": {
86
- "content": "<|end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": true,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "32008": {
94
- "content": "<|raw|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": true,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "32009": {
102
- "content": "<|continue|>",
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": true,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "32011": {
118
- "content": "<|function_list|>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": true,
122
- "single_word": false,
123
- "special": true
124
- },
125
- "32012": {
126
- "content": "<|calc|>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": true,
130
- "single_word": false,
131
- "special": true
132
- },
133
- "32013": {
134
- "content": "<|code|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": true,
138
- "single_word": false,
139
- "special": true
140
- },
141
- "32014": {
142
- "content": "<|/code|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": true,
146
- "single_word": false,
147
- "special": true
148
- },
149
- "32015": {
150
- "content": "<|summary|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": true,
154
- "single_word": false,
155
- "special": true
156
- },
157
- "32016": {
158
- "content": "<|resource|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": true,
162
- "single_word": false,
163
- "special": true
164
- },
165
- "32017": {
166
- "content": "<|assistant_mask|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": true,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "32018": {
174
- "content": "<|start|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": true,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "32019": {
182
- "content": "<|message|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": true,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "32020": {
190
- "content": "<|fim_prefix|>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": true,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "32021": {
198
- "content": "<|fim_middle|>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": true,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "32022": {
206
- "content": "<|fim_suffix|>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": true,
210
- "single_word": false,
211
- "special": true
212
- },
213
- "32023": {
214
- "content": "<|meta_start|>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": true,
218
- "single_word": false,
219
- "special": true
220
- },
221
- "32024": {
222
- "content": "<|ipynb_marker|>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": true,
226
- "single_word": false,
227
- "special": true
228
- },
229
- "32025": {
230
- "content": "<|diff_marker|>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": true,
234
- "single_word": false,
235
- "special": true
236
- },
237
- "32026": {
238
- "content": "<|ghissue|>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": true,
242
- "single_word": false,
243
- "special": true
244
- },
245
- "32027": {
246
- "content": "<|ghreview|>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": true,
250
- "single_word": false,
251
- "special": true
252
- },
253
- "32028": {
254
- "content": "<|disc_start|>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": true,
258
- "single_word": false,
259
- "special": true
260
- },
261
- "32029": {
262
- "content": "<|disc_sep|>",
263
- "lstrip": false,
264
- "normalized": false,
265
- "rstrip": true,
266
- "single_word": false,
267
- "special": true
268
- },
269
- "32030": {
270
- "content": "<|disc_thread|><|query|>",
271
- "lstrip": false,
272
- "normalized": false,
273
- "rstrip": true,
274
- "single_word": false,
275
- "special": true
276
- },
277
- "32031": {
278
- "content": "<|/query|>",
279
- "lstrip": false,
280
- "normalized": false,
281
- "rstrip": true,
282
- "single_word": false,
283
- "special": true
284
- },
285
- "32032": {
286
- "content": "<|data|>",
287
- "lstrip": false,
288
- "normalized": false,
289
- "rstrip": true,
290
- "single_word": false,
291
- "special": true
292
- },
293
- "32033": {
294
- "content": "<|/data|>",
295
- "lstrip": false,
296
- "normalized": false,
297
- "rstrip": true,
298
- "single_word": false,
299
- "special": true
300
- },
301
- "32034": {
302
- "content": "<|sys|>",
303
- "lstrip": false,
304
- "normalized": false,
305
- "rstrip": true,
306
- "single_word": false,
307
- "special": true
308
- },
309
- "32035": {
310
- "content": "<|/sys|>",
311
- "lstrip": false,
312
- "normalized": false,
313
- "rstrip": true,
314
- "single_word": false,
315
- "special": true
316
- },
317
- "32036": {
318
- "content": "<|inst|>",
319
- "lstrip": false,
320
- "normalized": false,
321
- "rstrip": true,
322
- "single_word": false,
323
- "special": true
324
- },
325
- "32037": {
326
- "content": "<|/inst|>",
327
- "lstrip": false,
328
- "normalized": false,
329
- "rstrip": true,
330
- "single_word": false,
331
- "special": true
332
- }
333
- },
334
- "additional_special_tokens": [
335
- "<|/inst|>"
336
- ],
337
- "bos_token": "<s>",
338
- "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
339
- "clean_up_tokenization_spaces": false,
340
- "eos_token": "<|endoftext|>",
341
- "legacy": false,
342
- "model_max_length": 131072,
343
- "pad_token": "<|endoftext|>",
344
- "padding_side": "left",
345
- "sp_model_kwargs": {},
346
- "tokenizer_class": "LlamaTokenizer",
347
- "unk_token": "<unk>",
348
- "use_default_system_prompt": false
349
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/genai_config.json β†’ genai_config.json RENAMED
File without changes
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi3-mini-128k-instruct-cpu-int4-rtn-block-32-acc-level-4.onnx β†’ onnx/decoder_model_merged_quantized.onnx RENAMED
File without changes
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi3-mini-128k-instruct-cpu-int4-rtn-block-32-acc-level-4.onnx.data β†’ onnx/decoder_model_merged_quantized.onnx.data RENAMED
File without changes
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/special_tokens_map.json β†’ special_tokens_map.json RENAMED
File without changes
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer.json β†’ tokenizer.json RENAMED
File without changes
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer.model β†’ tokenizer.model RENAMED
File without changes
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer_config.json β†’ tokenizer_config.json RENAMED
File without changes