Hugging Face's logo

tszs
/
prottex-cc

Safetensors
Model card Files
xet
 Community
tszs commited on
Commit
665b453
·
verified ·
1 Parent(s): 8e551fc

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. .gitattributes +2 -0
  2. X16N16_projection_checkpoint/16_shot_last_16_token_prefix_proj.safetensors +3 -0
  3. X16N16_projection_checkpoint/optimizer.pt +3 -0
  4. X16N16_projection_checkpoint/rng_state_0.pth +3 -0
  5. X16N16_projection_checkpoint/rng_state_1.pth +3 -0
  6. X16N16_projection_checkpoint/rng_state_2.pth +3 -0
  7. X16N16_projection_checkpoint/rng_state_3.pth +3 -0
  8. X16N16_projection_checkpoint/scheduler.pt +3 -0
  9. X16N16_projection_checkpoint/special_tokens_map.json +23 -0
  10. X16N16_projection_checkpoint/tokenizer.json +3 -0
  11. X16N16_projection_checkpoint/tokenizer_config.json +0 -0
  12. X16N16_projection_checkpoint/trainer_state.json +401 -0
  13. X16N16_projection_checkpoint/training_args.bin +3 -0
  14. prottex_joint_embed/config.json +30 -0
  15. prottex_joint_embed/generation_config.json +9 -0
  16. prottex_joint_embed/model-00001-of-00009.safetensors +3 -0
  17. prottex_joint_embed/model-00002-of-00009.safetensors +3 -0
  18. prottex_joint_embed/model-00003-of-00009.safetensors +3 -0
  19. prottex_joint_embed/model-00004-of-00009.safetensors +3 -0
  20. prottex_joint_embed/model-00005-of-00009.safetensors +3 -0
  21. prottex_joint_embed/model-00006-of-00009.safetensors +3 -0
  22. prottex_joint_embed/model-00007-of-00009.safetensors +3 -0
  23. prottex_joint_embed/model-00008-of-00009.safetensors +3 -0
  24. prottex_joint_embed/model-00009-of-00009.safetensors +3 -0
  25. prottex_joint_embed/model.safetensors.index.json +298 -0
  26. prottex_joint_embed/special_tokens_map.json +23 -0
  27. prottex_joint_embed/tokenizer.json +3 -0
  28. prottex_joint_embed/tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ X16N16_projection_checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ prottex_joint_embed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
X16N16_projection_checkpoint/16_shot_last_16_token_prefix_proj.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f50874a5766369e5936ee517d1cf8b293f39fa7302f346211c2b3de87ddbae3
3
+ size 67125400
X16N16_projection_checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e80f454ca9304d4f71eac3af85322c2972eb4c9a00ce8b63978afe24089740dd
3
+ size 134253404
X16N16_projection_checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c5e18f922d0af74d820247ae97bee506ab412554a58345ddf2558abc94ee3e3
3
+ size 15024
X16N16_projection_checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2dcca6d9741f46592359768ea2212b9321da6408d1fd7d3a80b017bf37f434
3
+ size 15024
X16N16_projection_checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69420ece2c255923c5cbb3c6c9c4a6b9cb38fb57e5d3033c8b7d436a1faf6f13
3
+ size 15024
X16N16_projection_checkpoint/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f278b40a1e23b88a657c4e5d03afa8dbbbe14dfeb16f6b4beedaece6cdd0b9
3
+ size 15024
X16N16_projection_checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39772bc879f790a25e0d105ade1b05ef60ec27d43a21929080222f58b660c42e
3
+ size 1064
X16N16_projection_checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|eot_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
X16N16_projection_checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebf958ef006b9b69a87af54a8b5884ef80a129c35d7e893ffce9025aad1a0f1a
3
+ size 17306081
X16N16_projection_checkpoint/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
X16N16_projection_checkpoint/trainer_state.json ADDED
@@ -0,0 +1,401 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 20000,
6
+ "global_step": 97947,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.020419206305450906,
13
+ "grad_norm": 0.039410658180713654,
14
+ "learning_rate": 9.98991631653945e-05,
15
+ "loss": 0.372,
16
+ "step": 2000
17
+ },
18
+ {
19
+ "epoch": 0.04083841261090181,
20
+ "grad_norm": 0.005198541097342968,
21
+ "learning_rate": 9.959298454390976e-05,
22
+ "loss": 0.065,
23
+ "step": 4000
24
+ },
25
+ {
26
+ "epoch": 0.06125761891635272,
27
+ "grad_norm": 0.06661669164896011,
28
+ "learning_rate": 9.908271387313857e-05,
29
+ "loss": 0.0685,
30
+ "step": 6000
31
+ },
32
+ {
33
+ "epoch": 0.08167682522180363,
34
+ "grad_norm": 0.006491110660135746,
35
+ "learning_rate": 9.837045109096221e-05,
36
+ "loss": 0.0687,
37
+ "step": 8000
38
+ },
39
+ {
40
+ "epoch": 0.10209603152725454,
41
+ "grad_norm": 0.0055190944112837315,
42
+ "learning_rate": 9.745912740170689e-05,
43
+ "loss": 0.0498,
44
+ "step": 10000
45
+ },
46
+ {
47
+ "epoch": 0.12251523783270545,
48
+ "grad_norm": 0.04117045924067497,
49
+ "learning_rate": 9.635249321323802e-05,
50
+ "loss": 0.0432,
51
+ "step": 12000
52
+ },
53
+ {
54
+ "epoch": 0.14293444413815634,
55
+ "grad_norm": 0.021597355604171753,
56
+ "learning_rate": 9.505510270275252e-05,
57
+ "loss": 0.0417,
58
+ "step": 14000
59
+ },
60
+ {
61
+ "epoch": 0.16335365044360725,
62
+ "grad_norm": 0.003780410159379244,
63
+ "learning_rate": 9.357229507478593e-05,
64
+ "loss": 0.0422,
65
+ "step": 16000
66
+ },
67
+ {
68
+ "epoch": 0.18377285674905816,
69
+ "grad_norm": 0.007895337417721748,
70
+ "learning_rate": 9.191017258856449e-05,
71
+ "loss": 0.0429,
72
+ "step": 18000
73
+ },
74
+ {
75
+ "epoch": 0.20419206305450907,
76
+ "grad_norm": 0.004307162947952747,
77
+ "learning_rate": 9.007557544512666e-05,
78
+ "loss": 0.0413,
79
+ "step": 20000
80
+ },
81
+ {
82
+ "epoch": 0.20419206305450907,
83
+ "eval_loss": 0.1096305251121521,
84
+ "eval_runtime": 1377.9634,
85
+ "eval_samples_per_second": 11.857,
86
+ "eval_steps_per_second": 2.965,
87
+ "step": 20000
88
+ },
89
+ {
90
+ "epoch": 0.22461126935995998,
91
+ "grad_norm": 0.007145540788769722,
92
+ "learning_rate": 8.807605363756247e-05,
93
+ "loss": 0.0446,
94
+ "step": 22000
95
+ },
96
+ {
97
+ "epoch": 0.2450304756654109,
98
+ "grad_norm": 0.0012220863718539476,
99
+ "learning_rate": 8.591983588021628e-05,
100
+ "loss": 0.0403,
101
+ "step": 24000
102
+ },
103
+ {
104
+ "epoch": 0.2654496819708618,
105
+ "grad_norm": 0.01538262702524662,
106
+ "learning_rate": 8.361579574472034e-05,
107
+ "loss": 0.0415,
108
+ "step": 26000
109
+ },
110
+ {
111
+ "epoch": 0.2858688882763127,
112
+ "grad_norm": 0.001653927145525813,
113
+ "learning_rate": 8.117341514222026e-05,
114
+ "loss": 0.0417,
115
+ "step": 28000
116
+ },
117
+ {
118
+ "epoch": 0.3062880945817636,
119
+ "grad_norm": 0.0205825362354517,
120
+ "learning_rate": 7.860274530207608e-05,
121
+ "loss": 0.038,
122
+ "step": 30000
123
+ },
124
+ {
125
+ "epoch": 0.3267073008872145,
126
+ "grad_norm": 0.018282199278473854,
127
+ "learning_rate": 7.591436540762474e-05,
128
+ "loss": 0.0369,
129
+ "step": 32000
130
+ },
131
+ {
132
+ "epoch": 0.3471265071926654,
133
+ "grad_norm": 0.0013706751633435488,
134
+ "learning_rate": 7.311933905923157e-05,
135
+ "loss": 0.0385,
136
+ "step": 34000
137
+ },
138
+ {
139
+ "epoch": 0.3675457134981163,
140
+ "grad_norm": 0.022714795544743538,
141
+ "learning_rate": 7.02291687438007e-05,
142
+ "loss": 0.0388,
143
+ "step": 36000
144
+ },
145
+ {
146
+ "epoch": 0.38796491980356723,
147
+ "grad_norm": 0.015217154286801815,
148
+ "learning_rate": 6.725574849811758e-05,
149
+ "loss": 0.0361,
150
+ "step": 38000
151
+ },
152
+ {
153
+ "epoch": 0.40838412610901814,
154
+ "grad_norm": 0.008922121487557888,
155
+ "learning_rate": 6.421131496082997e-05,
156
+ "loss": 0.0354,
157
+ "step": 40000
158
+ },
159
+ {
160
+ "epoch": 0.40838412610901814,
161
+ "eval_loss": 0.10438187420368195,
162
+ "eval_runtime": 1483.2608,
163
+ "eval_samples_per_second": 11.016,
164
+ "eval_steps_per_second": 2.754,
165
+ "step": 40000
166
+ },
167
+ {
168
+ "epoch": 0.42880333241446905,
169
+ "grad_norm": 0.004572518169879913,
170
+ "learning_rate": 6.110839701450578e-05,
171
+ "loss": 0.0352,
172
+ "step": 42000
173
+ },
174
+ {
175
+ "epoch": 0.44922253871991996,
176
+ "grad_norm": 0.004590547177940607,
177
+ "learning_rate": 5.795976422500715e-05,
178
+ "loss": 0.036,
179
+ "step": 44000
180
+ },
181
+ {
182
+ "epoch": 0.46964174502537087,
183
+ "grad_norm": 0.002056117169559002,
184
+ "learning_rate": 5.477837429037078e-05,
185
+ "loss": 0.0372,
186
+ "step": 46000
187
+ },
188
+ {
189
+ "epoch": 0.4900609513308218,
190
+ "grad_norm": 0.002131904009729624,
191
+ "learning_rate": 5.1577319715460226e-05,
192
+ "loss": 0.035,
193
+ "step": 48000
194
+ },
195
+ {
196
+ "epoch": 0.5104801576362726,
197
+ "grad_norm": 0.011025852523744106,
198
+ "learning_rate": 4.836977393184203e-05,
199
+ "loss": 0.0355,
200
+ "step": 50000
201
+ },
202
+ {
203
+ "epoch": 0.5308993639417235,
204
+ "grad_norm": 0.00647546723484993,
205
+ "learning_rate": 4.516893708462101e-05,
206
+ "loss": 0.0354,
207
+ "step": 52000
208
+ },
209
+ {
210
+ "epoch": 0.5513185702471745,
211
+ "grad_norm": 0.007355783600360155,
212
+ "learning_rate": 4.198798170934003e-05,
213
+ "loss": 0.0355,
214
+ "step": 54000
215
+ },
216
+ {
217
+ "epoch": 0.5717377765526254,
218
+ "grad_norm": 0.020101584494113922,
219
+ "learning_rate": 3.883999852250261e-05,
220
+ "loss": 0.037,
221
+ "step": 56000
222
+ },
223
+ {
224
+ "epoch": 0.5921569828580763,
225
+ "grad_norm": 0.00778984697535634,
226
+ "learning_rate": 3.57379425488089e-05,
227
+ "loss": 0.036,
228
+ "step": 58000
229
+ },
230
+ {
231
+ "epoch": 0.6125761891635272,
232
+ "grad_norm": 0.007056688889861107,
233
+ "learning_rate": 3.269457980680965e-05,
234
+ "loss": 0.035,
235
+ "step": 60000
236
+ },
237
+ {
238
+ "epoch": 0.6125761891635272,
239
+ "eval_loss": 0.10535352677106857,
240
+ "eval_runtime": 1556.8983,
241
+ "eval_samples_per_second": 10.495,
242
+ "eval_steps_per_second": 2.624,
243
+ "step": 60000
244
+ },
245
+ {
246
+ "epoch": 0.6329953954689781,
247
+ "grad_norm": 0.008058023639023304,
248
+ "learning_rate": 2.972243477238484e-05,
249
+ "loss": 0.0343,
250
+ "step": 62000
251
+ },
252
+ {
253
+ "epoch": 0.653414601774429,
254
+ "grad_norm": 0.012894408777356148,
255
+ "learning_rate": 2.6833738836252916e-05,
256
+ "loss": 0.0356,
257
+ "step": 64000
258
+ },
259
+ {
260
+ "epoch": 0.6738338080798799,
261
+ "grad_norm": 0.016047609969973564,
262
+ "learning_rate": 2.404037996762552e-05,
263
+ "loss": 0.0341,
264
+ "step": 66000
265
+ },
266
+ {
267
+ "epoch": 0.6942530143853308,
268
+ "grad_norm": 0.01276053674519062,
269
+ "learning_rate": 2.1353853791158717e-05,
270
+ "loss": 0.0338,
271
+ "step": 68000
272
+ },
273
+ {
274
+ "epoch": 0.7146722206907817,
275
+ "grad_norm": 0.005056174471974373,
276
+ "learning_rate": 1.8785216278535968e-05,
277
+ "loss": 0.0341,
278
+ "step": 70000
279
+ },
280
+ {
281
+ "epoch": 0.7350914269962326,
282
+ "grad_norm": 0.0010588251752778888,
283
+ "learning_rate": 1.6345038249373175e-05,
284
+ "loss": 0.0353,
285
+ "step": 72000
286
+ },
287
+ {
288
+ "epoch": 0.7555106333016836,
289
+ "grad_norm": 0.002015323843806982,
290
+ "learning_rate": 1.4043361868689698e-05,
291
+ "loss": 0.0365,
292
+ "step": 74000
293
+ },
294
+ {
295
+ "epoch": 0.7759298396071345,
296
+ "grad_norm": 0.007054855115711689,
297
+ "learning_rate": 1.1889659319973779e-05,
298
+ "loss": 0.0348,
299
+ "step": 76000
300
+ },
301
+ {
302
+ "epoch": 0.7963490459125854,
303
+ "grad_norm": 0.012270783074200153,
304
+ "learning_rate": 9.892793823916058e-06,
305
+ "loss": 0.0373,
306
+ "step": 78000
307
+ },
308
+ {
309
+ "epoch": 0.8167682522180363,
310
+ "grad_norm": 0.0010521231452003121,
311
+ "learning_rate": 8.06098316323296e-06,
312
+ "loss": 0.0372,
313
+ "step": 80000
314
+ },
315
+ {
316
+ "epoch": 0.8167682522180363,
317
+ "eval_loss": 0.10380256921052933,
318
+ "eval_runtime": 1404.8485,
319
+ "eval_samples_per_second": 11.63,
320
+ "eval_steps_per_second": 2.908,
321
+ "step": 80000
322
+ },
323
+ {
324
+ "epoch": 0.8371874585234872,
325
+ "grad_norm": 0.002963329665362835,
326
+ "learning_rate": 6.401765863687359e-06,
327
+ "loss": 0.0404,
328
+ "step": 82000
329
+ },
330
+ {
331
+ "epoch": 0.8576066648289381,
332
+ "grad_norm": 0.004744437523186207,
333
+ "learning_rate": 4.921970170483503e-06,
334
+ "loss": 0.0452,
335
+ "step": 84000
336
+ },
337
+ {
338
+ "epoch": 0.878025871134389,
339
+ "grad_norm": 0.005239036865532398,
340
+ "learning_rate": 3.627685947708592e-06,
341
+ "loss": 0.0439,
342
+ "step": 86000
343
+ },
344
+ {
345
+ "epoch": 0.8984450774398399,
346
+ "grad_norm": 0.016509557142853737,
347
+ "learning_rate": 2.524239616464641e-06,
348
+ "loss": 0.0448,
349
+ "step": 88000
350
+ },
351
+ {
352
+ "epoch": 0.9188642837452908,
353
+ "grad_norm": 0.010666937567293644,
354
+ "learning_rate": 1.616172234828528e-06,
355
+ "loss": 0.0443,
356
+ "step": 90000
357
+ },
358
+ {
359
+ "epoch": 0.9392834900507417,
360
+ "grad_norm": 0.004125706851482391,
361
+ "learning_rate": 9.072208098489964e-07,
362
+ "loss": 0.0423,
363
+ "step": 92000
364
+ },
365
+ {
366
+ "epoch": 0.9597026963561927,
367
+ "grad_norm": 0.012792402878403664,
368
+ "learning_rate": 4.003029184877771e-07,
369
+ "loss": 0.044,
370
+ "step": 94000
371
+ },
372
+ {
373
+ "epoch": 0.9801219026616436,
374
+ "grad_norm": 0.05335747450590134,
375
+ "learning_rate": 9.750470079509799e-08,
376
+ "loss": 0.0413,
377
+ "step": 96000
378
+ }
379
+ ],
380
+ "logging_steps": 2000,
381
+ "max_steps": 97947,
382
+ "num_input_tokens_seen": 0,
383
+ "num_train_epochs": 1,
384
+ "save_steps": 20000,
385
+ "stateful_callbacks": {
386
+ "TrainerControl": {
387
+ "args": {
388
+ "should_epoch_stop": false,
389
+ "should_evaluate": false,
390
+ "should_log": false,
391
+ "should_save": true,
392
+ "should_training_stop": true
393
+ },
394
+ "attributes": {}
395
+ }
396
+ },
397
+ "total_flos": 1.3798973062911099e+19,
398
+ "train_batch_size": 1,
399
+ "trial_name": null,
400
+ "trial_params": null
401
+ }
X16N16_projection_checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a85c41e6b1b0eceff022f74aaae5ebc2e75722ac53d3e87da771b14d829f41
3
+ size 5496
prottex_joint_embed/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/wp/2024_35wp/workspace/250423/protex_model",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 500000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.46.1",
28
+ "use_cache": true,
29
+ "vocab_size": 128832
30
+ }
prottex_joint_embed/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": 128001,
5
+ "max_length": 4096,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.46.1"
9
+ }
prottex_joint_embed/model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa99e4e54ab77cc049245373a8e7d6fb065bab1d95e781998712ac31ee3c5ac
3
+ size 1978173968
prottex_joint_embed/model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0731aff544100377b071ffefe3082b7768f629824698893428e31ac8905419c9
3
+ size 1895895336
prottex_joint_embed/model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cccb4f2a4fa986f835e6139336a627aab526173ae75dcf55db113697591b752
3
+ size 1979798040
prottex_joint_embed/model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3abf4fc17bef2265f5aac7a3cf1f11baa32856af3bcd64e8cb4c2cf28c20a15e
3
+ size 1946227368
prottex_joint_embed/model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9e8fe0e2abe66d48bac202ba59980656e8bfad86e0b95741abd6aeb6468310
3
+ size 1979798064
prottex_joint_embed/model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc23e996fcbd57090ad6afb1b5753599051ab1253761a8e36c87c0680cb9d485
3
+ size 1946227368
prottex_joint_embed/model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:761269f4c026a4c820d810be4c8b28837adeecbe0e7408cbb4a413633f0aed26
3
+ size 1979798064
prottex_joint_embed/model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d3bd0594c9780b90672dc1eaccfc6d5cc326dc3b10436f3b1f2a41483a330a6
3
+ size 1308683424
prottex_joint_embed/model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03389ef91f7bcb2b6bb70ce0ebe655d4bd50261535191d7cac4c59ddac6ff134
3
+ size 1055391872
prottex_joint_embed/model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16069959680
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00009-of-00009.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00005-of-00009.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00009.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00006-of-00009.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00007-of-00009.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00007-of-00009.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00007-of-00009.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00007-of-00009.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00008-of-00009.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00008-of-00009.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00008-of-00009.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
296
+ "model.norm.weight": "model-00008-of-00009.safetensors"
297
+ }
298
+ }
prottex_joint_embed/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|eot_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
prottex_joint_embed/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebf958ef006b9b69a87af54a8b5884ef80a129c35d7e893ffce9025aad1a0f1a
3
+ size 17306081
prottex_joint_embed/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff