PakNin commited on
Commit
b8b877f
·
verified ·
1 Parent(s): 24bc07e

Upload folder using huggingface_hub

Browse files
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|' + message['role'] + '|>' + '
2
+ ' + message['content'] + '<|end|>
3
+ ' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
4
+ ' }}{% else %}{{ eos_token }}{% endif %}
config.json ADDED
@@ -0,0 +1,366 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PhimoeForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_slimmoe.PhiMoEConfig",
9
+ "AutoModelForCausalLM": "modeling_slimmoe.PhiMoEForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": 32000,
14
+ "expert_dropout": 0.0,
15
+ "head_dim": 128,
16
+ "hidden_act": "silu",
17
+ "hidden_dropout": 0.0,
18
+ "hidden_size": 4096,
19
+ "initializer_range": 0.02,
20
+ "input_jitter_noise": 0.01,
21
+ "intermediate_size": 960,
22
+ "is_pruned": true,
23
+ "lm_head_bias": true,
24
+ "max_position_embeddings": 4096,
25
+ "model_type": "phimoe",
26
+ "num_attention_heads": 32,
27
+ "num_experts_per_tok": 2,
28
+ "num_hidden_layers": 32,
29
+ "num_key_value_heads": 8,
30
+ "num_local_experts": 48,
31
+ "old_to_new_mapping": {
32
+ "0": {
33
+ "12": 3,
34
+ "14": 4,
35
+ "4": 0,
36
+ "5": 1,
37
+ "8": 2
38
+ },
39
+ "1": {
40
+ "1": 0,
41
+ "10": 6,
42
+ "12": 7,
43
+ "14": 8,
44
+ "3": 1,
45
+ "4": 2,
46
+ "5": 3,
47
+ "7": 4,
48
+ "8": 5
49
+ },
50
+ "10": {
51
+ "1": 0,
52
+ "13": 6,
53
+ "15": 7,
54
+ "2": 1,
55
+ "4": 2,
56
+ "6": 3,
57
+ "7": 4,
58
+ "8": 5
59
+ },
60
+ "11": {
61
+ "0": 0,
62
+ "11": 3,
63
+ "12": 4,
64
+ "14": 5,
65
+ "15": 6,
66
+ "6": 1,
67
+ "8": 2
68
+ },
69
+ "12": {
70
+ "0": 0,
71
+ "10": 3,
72
+ "11": 4,
73
+ "12": 5,
74
+ "14": 6,
75
+ "15": 7,
76
+ "5": 1,
77
+ "6": 2
78
+ },
79
+ "13": {
80
+ "11": 2,
81
+ "13": 3,
82
+ "14": 4,
83
+ "2": 0,
84
+ "3": 1
85
+ },
86
+ "14": {
87
+ "11": 2,
88
+ "12": 3,
89
+ "13": 4,
90
+ "14": 5,
91
+ "2": 0,
92
+ "3": 1
93
+ },
94
+ "15": {
95
+ "0": 0,
96
+ "1": 1,
97
+ "10": 5,
98
+ "12": 6,
99
+ "14": 7,
100
+ "3": 2,
101
+ "4": 3,
102
+ "7": 4
103
+ },
104
+ "16": {
105
+ "1": 0,
106
+ "11": 5,
107
+ "12": 6,
108
+ "14": 7,
109
+ "2": 1,
110
+ "3": 2,
111
+ "5": 3,
112
+ "7": 4
113
+ },
114
+ "17": {
115
+ "1": 0,
116
+ "12": 7,
117
+ "14": 8,
118
+ "2": 1,
119
+ "3": 2,
120
+ "4": 3,
121
+ "5": 4,
122
+ "6": 5,
123
+ "7": 6
124
+ },
125
+ "18": {
126
+ "10": 6,
127
+ "12": 7,
128
+ "14": 8,
129
+ "3": 0,
130
+ "4": 1,
131
+ "5": 2,
132
+ "7": 3,
133
+ "8": 4,
134
+ "9": 5
135
+ },
136
+ "19": {
137
+ "0": 0,
138
+ "10": 6,
139
+ "14": 7,
140
+ "3": 1,
141
+ "4": 2,
142
+ "5": 3,
143
+ "6": 4,
144
+ "7": 5
145
+ },
146
+ "2": {
147
+ "1": 0,
148
+ "10": 8,
149
+ "11": 9,
150
+ "12": 10,
151
+ "13": 11,
152
+ "14": 12,
153
+ "15": 13,
154
+ "2": 1,
155
+ "3": 2,
156
+ "4": 3,
157
+ "5": 4,
158
+ "6": 5,
159
+ "7": 6,
160
+ "8": 7
161
+ },
162
+ "20": {
163
+ "1": 0,
164
+ "12": 5,
165
+ "13": 6,
166
+ "14": 7,
167
+ "15": 8,
168
+ "2": 1,
169
+ "5": 2,
170
+ "6": 3,
171
+ "7": 4
172
+ },
173
+ "21": {
174
+ "14": 3,
175
+ "15": 4,
176
+ "4": 0,
177
+ "6": 1,
178
+ "9": 2
179
+ },
180
+ "22": {
181
+ "0": 0,
182
+ "1": 1,
183
+ "14": 7,
184
+ "15": 8,
185
+ "3": 2,
186
+ "4": 3,
187
+ "6": 4,
188
+ "8": 5,
189
+ "9": 6
190
+ },
191
+ "23": {
192
+ "0": 0,
193
+ "10": 5,
194
+ "12": 6,
195
+ "14": 7,
196
+ "2": 1,
197
+ "3": 2,
198
+ "5": 3,
199
+ "9": 4
200
+ },
201
+ "24": {
202
+ "1": 0,
203
+ "11": 5,
204
+ "14": 6,
205
+ "3": 1,
206
+ "5": 2,
207
+ "7": 3,
208
+ "9": 4
209
+ },
210
+ "25": {
211
+ "0": 0,
212
+ "10": 5,
213
+ "11": 6,
214
+ "12": 7,
215
+ "15": 8,
216
+ "2": 1,
217
+ "4": 2,
218
+ "8": 3,
219
+ "9": 4
220
+ },
221
+ "26": {
222
+ "11": 4,
223
+ "12": 5,
224
+ "15": 6,
225
+ "2": 0,
226
+ "3": 1,
227
+ "4": 2,
228
+ "8": 3
229
+ },
230
+ "27": {
231
+ "0": 0,
232
+ "10": 5,
233
+ "11": 6,
234
+ "12": 7,
235
+ "13": 8,
236
+ "15": 9,
237
+ "2": 1,
238
+ "4": 2,
239
+ "5": 3,
240
+ "9": 4
241
+ },
242
+ "28": {
243
+ "1": 0,
244
+ "10": 5,
245
+ "11": 6,
246
+ "12": 7,
247
+ "13": 8,
248
+ "4": 1,
249
+ "6": 2,
250
+ "7": 3,
251
+ "9": 4
252
+ },
253
+ "29": {
254
+ "1": 0,
255
+ "10": 6,
256
+ "11": 7,
257
+ "4": 1,
258
+ "6": 2,
259
+ "7": 3,
260
+ "8": 4,
261
+ "9": 5
262
+ },
263
+ "3": {
264
+ "1": 0,
265
+ "10": 6,
266
+ "11": 7,
267
+ "13": 8,
268
+ "14": 9,
269
+ "15": 10,
270
+ "4": 1,
271
+ "6": 2,
272
+ "7": 3,
273
+ "8": 4,
274
+ "9": 5
275
+ },
276
+ "30": {
277
+ "1": 0,
278
+ "10": 4,
279
+ "11": 5,
280
+ "12": 6,
281
+ "15": 7,
282
+ "3": 1,
283
+ "7": 2,
284
+ "9": 3
285
+ },
286
+ "31": {
287
+ "1": 0,
288
+ "10": 6,
289
+ "12": 7,
290
+ "15": 8,
291
+ "2": 1,
292
+ "4": 2,
293
+ "7": 3,
294
+ "8": 4,
295
+ "9": 5
296
+ },
297
+ "4": {
298
+ "10": 6,
299
+ "13": 7,
300
+ "15": 8,
301
+ "4": 0,
302
+ "5": 1,
303
+ "6": 2,
304
+ "7": 3,
305
+ "8": 4,
306
+ "9": 5
307
+ },
308
+ "5": {
309
+ "12": 3,
310
+ "13": 4,
311
+ "15": 5,
312
+ "4": 0,
313
+ "7": 1,
314
+ "9": 2
315
+ },
316
+ "6": {
317
+ "0": 0,
318
+ "1": 1,
319
+ "10": 6,
320
+ "13": 7,
321
+ "15": 8,
322
+ "5": 2,
323
+ "6": 3,
324
+ "7": 4,
325
+ "9": 5
326
+ },
327
+ "7": {
328
+ "1": 0,
329
+ "10": 3,
330
+ "12": 4,
331
+ "13": 5,
332
+ "3": 1,
333
+ "7": 2
334
+ },
335
+ "8": {
336
+ "1": 0,
337
+ "10": 7,
338
+ "12": 8,
339
+ "14": 9,
340
+ "3": 1,
341
+ "4": 2,
342
+ "5": 3,
343
+ "6": 4,
344
+ "7": 5,
345
+ "8": 6
346
+ },
347
+ "9": {
348
+ "0": 0,
349
+ "11": 3,
350
+ "4": 1,
351
+ "6": 2
352
+ }
353
+ },
354
+ "output_router_logits": false,
355
+ "pruned": true,
356
+ "rms_norm_eps": 1e-05,
357
+ "rope_scaling": null,
358
+ "rope_theta": 10000.0,
359
+ "router_aux_loss_coef": 0.0,
360
+ "router_jitter_noise": 0.01,
361
+ "sliding_window": 2047,
362
+ "tie_word_embeddings": false,
363
+ "transformers_version": "4.57.3",
364
+ "use_cache": true,
365
+ "vocab_size": 32064
366
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32001,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.57.3"
11
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c36badc2adb43d332183f747236cab625e595ea69570e21acd2d68373daaa828
3
+ size 4997213700
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae9504c70847ca3d43da4540d5b9324f72a0f62855c59351a30793b301acc185
3
+ size 4290394588
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
pruning_map.txt ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Pruned Experts by Original Layer (Target layer, Expert ID):
2
+ Layer 0: [0, 1, 2, 3, 6, 7, 9, 10, 11, 13, 15]
3
+ Layer 1: [0, 2, 6, 9, 11, 13, 15]
4
+ Layer 2: [0, 9]
5
+ Layer 3: [0, 2, 3, 5, 12]
6
+ Layer 4: [0, 1, 2, 3, 11, 12, 14]
7
+ Layer 5: [0, 1, 2, 3, 5, 6, 8, 10, 11, 14]
8
+ Layer 6: [2, 3, 4, 8, 11, 12, 14]
9
+ Layer 7: [0, 2, 4, 5, 6, 8, 9, 11, 14, 15]
10
+ Layer 8: [0, 2, 9, 11, 13, 15]
11
+ Layer 9: [1, 2, 3, 5, 7, 8, 9, 10, 12, 13, 14, 15]
12
+ Layer 10: [0, 3, 5, 9, 10, 11, 12, 14]
13
+ Layer 11: [1, 2, 3, 4, 5, 7, 9, 10, 13]
14
+ Layer 12: [1, 2, 3, 4, 7, 8, 9, 13]
15
+ Layer 13: [0, 1, 4, 5, 6, 7, 8, 9, 10, 12, 15]
16
+ Layer 14: [0, 1, 4, 5, 6, 7, 8, 9, 10, 15]
17
+ Layer 15: [2, 5, 6, 8, 9, 11, 13, 15]
18
+ Layer 16: [0, 4, 6, 8, 9, 10, 13, 15]
19
+ Layer 17: [0, 8, 9, 10, 11, 13, 15]
20
+ Layer 18: [0, 1, 2, 6, 11, 13, 15]
21
+ Layer 19: [1, 2, 8, 9, 11, 12, 13, 15]
22
+ Layer 20: [0, 3, 4, 8, 9, 10, 11]
23
+ Layer 21: [0, 1, 2, 3, 5, 7, 8, 10, 11, 12, 13]
24
+ Layer 22: [2, 5, 7, 10, 11, 12, 13]
25
+ Layer 23: [1, 4, 6, 7, 8, 11, 13, 15]
26
+ Layer 24: [0, 2, 4, 6, 8, 10, 12, 13, 15]
27
+ Layer 25: [1, 3, 5, 6, 7, 13, 14]
28
+ Layer 26: [0, 1, 5, 6, 7, 9, 10, 13, 14]
29
+ Layer 27: [1, 3, 6, 7, 8, 14]
30
+ Layer 28: [0, 2, 3, 5, 8, 14, 15]
31
+ Layer 29: [0, 2, 3, 5, 12, 13, 14, 15]
32
+ Layer 30: [0, 2, 4, 5, 6, 8, 13, 14]
33
+ Layer 31: [0, 3, 5, 6, 11, 13, 14]
rexmoe_routers.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ef9516c7741a22739c75df69e7cdaa4d2e71425f5e9702627c39016997f031
3
+ size 12623346
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "extra_special_tokens": {},
123
+ "legacy": false,
124
+ "model_max_length": 4096,
125
+ "pad_token": "<|endoftext|>",
126
+ "padding_side": "left",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizerFast",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }