tensor-tech pruning commited on
Commit
a0c6d00
·
verified ·
0 Parent(s):

Duplicate from pruning/sn38-v4-1-1

Browse files

Co-authored-by: Pruning <[email protected]>

.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,292 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "all_reduce_scores": {
3
+ "0": "NOT_ALIVE",
4
+ "1": "NOT_ALIVE",
5
+ "10": "NOT_ALIVE",
6
+ "100": "NOT_ALIVE",
7
+ "101": "NOT_ALIVE",
8
+ "102": "NOT_ALIVE",
9
+ "103": "NOT_ALIVE",
10
+ "104": "NOT_ALIVE",
11
+ "105": "NOT_ALIVE",
12
+ "106": "NOT_ALIVE",
13
+ "107": "NOT_ALIVE",
14
+ "108": "NOT_ALIVE",
15
+ "109": "NON_PARTICIPATING",
16
+ "11": "NOT_ALIVE",
17
+ "110": "NOT_ALIVE",
18
+ "111": "NOT_ALIVE",
19
+ "112": "NON_PARTICIPATING",
20
+ "113": "NON_PARTICIPATING",
21
+ "114": "NON_PARTICIPATING",
22
+ "115": "NOT_ALIVE",
23
+ "116": "NON_PARTICIPATING",
24
+ "117": "NON_PARTICIPATING",
25
+ "118": "NOT_ALIVE",
26
+ "119": "NOT_ALIVE",
27
+ "12": "NOT_ALIVE",
28
+ "120": "NON_PARTICIPATING",
29
+ "121": "NOT_ALIVE",
30
+ "122": "NOT_ALIVE",
31
+ "123": "NON_PARTICIPATING",
32
+ "124": "NOT_ALIVE",
33
+ "125": "SUCCESS",
34
+ "126": "NON_PARTICIPATING",
35
+ "127": "NON_PARTICIPATING",
36
+ "128": "NON_PARTICIPATING",
37
+ "129": "NON_PARTICIPATING",
38
+ "13": "NOT_ALIVE",
39
+ "130": "NOT_ALIVE",
40
+ "131": "NOT_ALIVE",
41
+ "132": "NON_PARTICIPATING",
42
+ "133": "NON_PARTICIPATING",
43
+ "134": "NON_PARTICIPATING",
44
+ "135": "NON_PARTICIPATING",
45
+ "136": "NOT_ALIVE",
46
+ "137": "NOT_ALIVE",
47
+ "138": "NON_PARTICIPATING",
48
+ "139": "NOT_ALIVE",
49
+ "14": "SUCCESS",
50
+ "140": "NOT_ALIVE",
51
+ "141": "NON_PARTICIPATING",
52
+ "142": "NOT_ALIVE",
53
+ "143": "NON_PARTICIPATING",
54
+ "144": "NOT_ALIVE",
55
+ "145": "NON_PARTICIPATING",
56
+ "146": "NOT_ALIVE",
57
+ "147": "NOT_ALIVE",
58
+ "148": "NOT_ALIVE",
59
+ "149": "NOT_ALIVE",
60
+ "15": "SUCCESS",
61
+ "150": "NOT_ALIVE",
62
+ "151": "NOT_ALIVE",
63
+ "152": "NON_PARTICIPATING",
64
+ "153": "NOT_ALIVE",
65
+ "154": "SUCCESS",
66
+ "155": "SUCCESS",
67
+ "156": "NON_PARTICIPATING",
68
+ "157": "NOT_ALIVE",
69
+ "158": "NOT_ALIVE",
70
+ "159": "NOT_ALIVE",
71
+ "16": "NOT_ALIVE",
72
+ "160": "NOT_ALIVE",
73
+ "161": "NOT_ALIVE",
74
+ "162": "NOT_ALIVE",
75
+ "163": "NOT_ALIVE",
76
+ "164": "NOT_ALIVE",
77
+ "165": "NOT_ALIVE",
78
+ "166": "NOT_ALIVE",
79
+ "167": "NON_PARTICIPATING",
80
+ "168": "NON_PARTICIPATING",
81
+ "169": "NOT_ALIVE",
82
+ "17": "NOT_ALIVE",
83
+ "170": "NOT_ALIVE",
84
+ "171": "NOT_ALIVE",
85
+ "172": "NOT_ALIVE",
86
+ "173": "NON_PARTICIPATING",
87
+ "174": "NOT_ALIVE",
88
+ "175": "NOT_ALIVE",
89
+ "176": "NOT_ALIVE",
90
+ "177": "NOT_ALIVE",
91
+ "178": "NOT_ALIVE",
92
+ "179": "NOT_ALIVE",
93
+ "18": "NON_PARTICIPATING",
94
+ "180": "NOT_ALIVE",
95
+ "181": "NOT_ALIVE",
96
+ "182": "NOT_ALIVE",
97
+ "183": "NON_PARTICIPATING",
98
+ "184": "NOT_ALIVE",
99
+ "185": "NOT_ALIVE",
100
+ "186": "NOT_ALIVE",
101
+ "187": "NON_PARTICIPATING",
102
+ "188": "NON_PARTICIPATING",
103
+ "189": "NOT_ALIVE",
104
+ "19": "NON_PARTICIPATING",
105
+ "190": "NOT_ALIVE",
106
+ "191": "NON_PARTICIPATING",
107
+ "192": "NOT_ALIVE",
108
+ "193": "NON_PARTICIPATING",
109
+ "194": "NOT_ALIVE",
110
+ "195": "NOT_ALIVE",
111
+ "196": "SUCCESS",
112
+ "197": "NON_PARTICIPATING",
113
+ "198": "NON_PARTICIPATING",
114
+ "199": "NON_PARTICIPATING",
115
+ "2": "NON_PARTICIPATING",
116
+ "20": "NOT_ALIVE",
117
+ "200": "NOT_ALIVE",
118
+ "201": "NOT_ALIVE",
119
+ "202": "NOT_ALIVE",
120
+ "203": "NOT_ALIVE",
121
+ "204": "NOT_ALIVE",
122
+ "205": "NOT_ALIVE",
123
+ "206": "NON_PARTICIPATING",
124
+ "207": "NOT_ALIVE",
125
+ "208": "NOT_ALIVE",
126
+ "209": "NOT_ALIVE",
127
+ "21": "NOT_ALIVE",
128
+ "210": "NOT_ALIVE",
129
+ "211": "NOT_ALIVE",
130
+ "212": "NON_PARTICIPATING",
131
+ "213": "NOT_ALIVE",
132
+ "214": "NOT_ALIVE",
133
+ "215": "SUCCESS",
134
+ "216": "NOT_ALIVE",
135
+ "217": "NON_PARTICIPATING",
136
+ "218": "NOT_ALIVE",
137
+ "219": "NOT_ALIVE",
138
+ "22": "NOT_ALIVE",
139
+ "220": "NOT_ALIVE",
140
+ "221": "NOT_ALIVE",
141
+ "222": "NON_PARTICIPATING",
142
+ "223": "NOT_ALIVE",
143
+ "224": "NOT_ALIVE",
144
+ "225": "NON_PARTICIPATING",
145
+ "226": "NOT_ALIVE",
146
+ "227": "NOT_ALIVE",
147
+ "228": "NON_PARTICIPATING",
148
+ "229": "NOT_ALIVE",
149
+ "23": "NON_PARTICIPATING",
150
+ "230": "NOT_ALIVE",
151
+ "231": "NOT_ALIVE",
152
+ "232": "NOT_ALIVE",
153
+ "233": "NOT_ALIVE",
154
+ "234": "NOT_ALIVE",
155
+ "235": "NOT_ALIVE",
156
+ "236": "NOT_ALIVE",
157
+ "237": "NOT_ALIVE",
158
+ "238": "NON_PARTICIPATING",
159
+ "239": "NOT_ALIVE",
160
+ "24": "NOT_ALIVE",
161
+ "240": "NON_PARTICIPATING",
162
+ "241": "SUCCESS",
163
+ "242": "NOT_ALIVE",
164
+ "243": "NON_PARTICIPATING",
165
+ "244": "NOT_ALIVE",
166
+ "245": "NOT_ALIVE",
167
+ "246": "NOT_ALIVE",
168
+ "247": "NON_PARTICIPATING",
169
+ "248": "NOT_ALIVE",
170
+ "249": "NOT_ALIVE",
171
+ "25": "SUCCESS",
172
+ "250": "SUCCESS",
173
+ "251": "NOT_ALIVE",
174
+ "252": "NOT_ALIVE",
175
+ "253": "NOT_ALIVE",
176
+ "254": "NON_PARTICIPATING",
177
+ "255": "NOT_ALIVE",
178
+ "26": "NOT_ALIVE",
179
+ "27": "NOT_ALIVE",
180
+ "28": "NOT_ALIVE",
181
+ "29": "NOT_ALIVE",
182
+ "3": "NON_PARTICIPATING",
183
+ "30": "SUCCESS",
184
+ "31": "NON_PARTICIPATING",
185
+ "32": "SUCCESS",
186
+ "33": "NOT_ALIVE",
187
+ "34": "NOT_ALIVE",
188
+ "35": "NON_PARTICIPATING",
189
+ "36": "NOT_ALIVE",
190
+ "37": "NOT_ALIVE",
191
+ "38": "NON_PARTICIPATING",
192
+ "39": "NON_PARTICIPATING",
193
+ "4": "NOT_ALIVE",
194
+ "40": "NON_PARTICIPATING",
195
+ "41": "NOT_ALIVE",
196
+ "42": "NOT_ALIVE",
197
+ "43": "NOT_ALIVE",
198
+ "44": "NOT_ALIVE",
199
+ "45": "NOT_ALIVE",
200
+ "46": "NON_PARTICIPATING",
201
+ "47": "SUCCESS",
202
+ "48": "NON_PARTICIPATING",
203
+ "49": "NON_PARTICIPATING",
204
+ "5": "NOT_ALIVE",
205
+ "50": "NOT_ALIVE",
206
+ "51": "NON_PARTICIPATING",
207
+ "52": "NON_PARTICIPATING",
208
+ "53": "NOT_ALIVE",
209
+ "54": "NOT_ALIVE",
210
+ "55": "NOT_ALIVE",
211
+ "56": "NON_PARTICIPATING",
212
+ "57": "NOT_ALIVE",
213
+ "58": "NON_PARTICIPATING",
214
+ "59": "NOT_ALIVE",
215
+ "6": "NON_PARTICIPATING",
216
+ "60": "NOT_ALIVE",
217
+ "61": "NOT_ALIVE",
218
+ "62": "NOT_ALIVE",
219
+ "63": "SUCCESS",
220
+ "64": "NOT_ALIVE",
221
+ "65": "NOT_ALIVE",
222
+ "66": "NON_PARTICIPATING",
223
+ "67": "NOT_ALIVE",
224
+ "68": "NOT_ALIVE",
225
+ "69": "NOT_ALIVE",
226
+ "7": "NOT_ALIVE",
227
+ "70": "NOT_ALIVE",
228
+ "71": "NON_PARTICIPATING",
229
+ "72": "NON_PARTICIPATING",
230
+ "73": "NOT_ALIVE",
231
+ "74": "NOT_ALIVE",
232
+ "75": "NON_PARTICIPATING",
233
+ "76": "NOT_ALIVE",
234
+ "77": "NON_PARTICIPATING",
235
+ "78": "NON_PARTICIPATING",
236
+ "79": "NON_PARTICIPATING",
237
+ "8": "NON_PARTICIPATING",
238
+ "80": "NOT_ALIVE",
239
+ "81": "NON_PARTICIPATING",
240
+ "82": "NOT_ALIVE",
241
+ "83": "NOT_ALIVE",
242
+ "84": "NOT_ALIVE",
243
+ "85": "NOT_ALIVE",
244
+ "86": "NOT_ALIVE",
245
+ "87": "NOT_ALIVE",
246
+ "88": "NOT_ALIVE",
247
+ "89": "NOT_ALIVE",
248
+ "9": "NOT_ALIVE",
249
+ "90": "NOT_ALIVE",
250
+ "91": "NON_PARTICIPATING",
251
+ "92": "NON_PARTICIPATING",
252
+ "93": "NOT_ALIVE",
253
+ "94": "SUCCESS",
254
+ "95": "NOT_ALIVE",
255
+ "96": "NOT_ALIVE",
256
+ "97": "NON_PARTICIPATING",
257
+ "98": "NOT_ALIVE",
258
+ "99": "NOT_ALIVE"
259
+ },
260
+ "architectures": [
261
+ "LlamaForCausalLM"
262
+ ],
263
+ "attention_bias": false,
264
+ "attention_dropout": 0.0,
265
+ "block_list": [
266
+ 6022295
267
+ ],
268
+ "bos_token_id": 1,
269
+ "eos_token_id": 2,
270
+ "head_dim": 64,
271
+ "hidden_act": "silu",
272
+ "hidden_size": 2048,
273
+ "initializer_range": 0.02,
274
+ "inner_step": 20,
275
+ "intermediate_size": 5632,
276
+ "last_allreduce_block": 6021778,
277
+ "max_position_embeddings": 2048,
278
+ "mlp_bias": false,
279
+ "model_type": "llama",
280
+ "num_attention_heads": 32,
281
+ "num_hidden_layers": 22,
282
+ "num_key_value_heads": 4,
283
+ "pretraining_tp": 1,
284
+ "rms_norm_eps": 1e-05,
285
+ "rope_scaling": null,
286
+ "rope_theta": 10000.0,
287
+ "tie_word_embeddings": false,
288
+ "torch_dtype": "float32",
289
+ "transformers_version": "4.53.1",
290
+ "use_cache": false,
291
+ "vocab_size": 32000
292
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.53.1",
6
+ "use_cache": false
7
+ }
inner_optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecedd7012712c013fe68b488e0a727cc98660407fdb27c157ffc5651bcb09fc2
3
+ size 8800564561
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf00aa0d250e8f90dcd68b4fbbfc139f5827fc57d987b034499b265964014ba
3
+ size 4400216536