Hugging Face's logo

OpenMol
/
PRESTO-yield

Safetensors
llama-lmm
finetuned
multimodal
Model card Files
xet
Community
hcaoaf commited on
Commit
17f8d95
·
verified ·
1 Parent(s): 7d8db41

Upload 9 files

Browse files
Files changed (9) hide show
  1. README.md +538 -3
  2. config.json +34 -0
  3. generation_config.json +7 -0
  4. model.safetensors.index.json +302 -0
  5. model_named_parameters.txt +295 -0
  6. special_tokens_map.json +51 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +46 -0
  9. training_args.bin +3 -0
README.md CHANGED
@@ -1,3 +1,538 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: apache-2.0
4
+ dataset: yield
5
+ tags:
6
+ - finetuned
7
+ - multimodal
8
+ inference: false
9
+ ---
10
+
11
+ These are weights for a version of `checkpoints/stage2/llava-moleculestm-vicuna-7b-v1.5-pretrain_all` finetuned for multimodal applications.
12
+
13
+ ### Modalities
14
+
15
+ * Molecule2DModality (use `<molecule_2d>` in text and provide `molecules`
16
+
17
+ ### Usage
18
+
19
+ GitHub: https://github.com/sshh12/bioagent (includes training scripts and basic inference server)
20
+
21
+ ### Dataset
22
+
23
+ yield (9515 examples)
24
+
25
+ ```
26
+ {'molecule_2d': [(tensor([[34, 0],
27
+ [ 5, 0],
28
+ [ 5, 0],
29
+ [ 5, 0],
30
+ [ 5, 0],
31
+ [ 6, 0],
32
+ [ 5, 0]]), tensor([[0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 1],
33
+ [1, 0, 2, 1, 3, 2, 4, 3, 5, 4, 6, 5, 1, 6]]), tensor([[0, 0],
34
+ [0, 0],
35
+ [3, 0],
36
+ [3, 0],
37
+ [3, 0],
38
+ [3, 0],
39
+ [3, 0],
40
+ [3, 0],
41
+ [3, 0],
42
+ [3, 0],
43
+ [3, 0],
44
+ [3, 0],
45
+ [3, 0],
46
+ [3, 0]])), (tensor([[5, 0],
47
+ [5, 0],
48
+ [5, 0],
49
+ [5, 0],
50
+ [5, 0],
51
+ [6, 0],
52
+ [5, 0],
53
+ [5, 0]]), tensor([[0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 4, 6, 6, 7, 7, 1],
54
+ [1, 0, 2, 1, 3, 2, 4, 3, 5, 4, 6, 4, 7, 6, 1, 7]]), tensor([[0, 0],
55
+ [0, 0],
56
+ [3, 0],
57
+ [3, 0],
58
+ [3, 0],
59
+ [3, 0],
60
+ [3, 0],
61
+ [3, 0],
62
+ [0, 0],
63
+ [0, 0],
64
+ [3, 0],
65
+ [3, 0],
66
+ [3, 0],
67
+ [3, 0],
68
+ [3, 0],
69
+ [3, 0]])), (tensor([[ 7, 0],
70
+ [15, 0],
71
+ [ 7, 0],
72
+ [ 7, 0],
73
+ [45, 0],
74
+ [ 6, 0],
75
+ [ 5, 0],
76
+ [ 5, 0],
77
+ [ 5, 0],
78
+ [ 5, 0],
79
+ [ 5, 0],
80
+ [ 5, 0],
81
+ [ 5, 0],
82
+ [ 5, 0],
83
+ [ 5, 0],
84
+ [ 5, 0],
85
+ [ 5, 0],
86
+ [ 5, 0],
87
+ [ 5, 0],
88
+ [ 8, 0],
89
+ [ 8, 0],
90
+ [ 8, 0]]), tensor([[ 0, 1, 1, 2, 1, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9,
91
+ 9, 10, 10, 11, 11, 12, 12, 13, 13, 14, 14, 15, 15, 16, 16, 17, 1, 18,
92
+ 18, 19, 18, 20, 18, 21, 17, 4, 11, 6, 17, 12],
93
+ [ 1, 0, 2, 1, 3, 1, 4, 3, 5, 4, 6, 5, 7, 6, 8, 7, 9, 8,
94
+ 10, 9, 11, 10, 12, 11, 13, 12, 14, 13, 15, 14, 16, 15, 17, 16, 18, 1,
95
+ 19, 18, 20, 18, 21, 18, 4, 17, 6, 11, 12, 17]]), tensor([[1, 0],
96
+ [1, 0],
97
+ [1, 0],
98
+ [1, 0],
99
+ [0, 0],
100
+ [0, 0],
101
+ [0, 0],
102
+ [0, 0],
103
+ [0, 0],
104
+ [0, 0],
105
+ [0, 0],
106
+ [0, 0],
107
+ [3, 0],
108
+ [3, 0],
109
+ [3, 0],
110
+ [3, 0],
111
+ [3, 0],
112
+ [3, 0],
113
+ [3, 0],
114
+ [3, 0],
115
+ [3, 0],
116
+ [3, 0],
117
+ [0, 0],
118
+ [0, 0],
119
+ [3, 0],
120
+ [3, 0],
121
+ [3, 0],
122
+ [3, 0],
123
+ [3, 0],
124
+ [3, 0],
125
+ [3, 0],
126
+ [3, 0],
127
+ [3, 0],
128
+ [3, 0],
129
+ [0, 0],
130
+ [0, 0],
131
+ [0, 0],
132
+ [0, 0],
133
+ [0, 0],
134
+ [0, 0],
135
+ [0, 0],
136
+ [0, 0],
137
+ [0, 0],
138
+ [0, 0],
139
+ [3, 0],
140
+ [3, 0],
141
+ [3, 0],
142
+ [3, 0]])), (tensor([[ 5, 0],
143
+ [ 7, 0],
144
+ [ 5, 0],
145
+ [ 5, 0],
146
+ [ 5, 0],
147
+ [ 5, 0],
148
+ [ 7, 0],
149
+ [ 5, 0],
150
+ [ 5, 0],
151
+ [14, 0],
152
+ [ 5, 0],
153
+ [ 5, 0],
154
+ [ 5, 0],
155
+ [ 5, 0],
156
+ [ 5, 0],
157
+ [ 5, 0],
158
+ [ 5, 0],
159
+ [ 5, 0],
160
+ [ 5, 0],
161
+ [ 5, 0],
162
+ [ 5, 0],
163
+ [ 5, 0],
164
+ [ 5, 0],
165
+ [ 5, 0],
166
+ [ 5, 0],
167
+ [ 5, 0],
168
+ [ 5, 0],
169
+ [ 5, 0],
170
+ [ 5, 0],
171
+ [ 5, 0],
172
+ [ 5, 0],
173
+ [ 5, 0],
174
+ [ 5, 0],
175
+ [ 5, 0],
176
+ [ 5, 0],
177
+ [ 5, 0],
178
+ [ 5, 0],
179
+ [ 5, 0],
180
+ [ 5, 0],
181
+ [ 5, 0],
182
+ [ 5, 0],
183
+ [ 5, 0],
184
+ [ 5, 0],
185
+ [ 5, 0],
186
+ [ 5, 0],
187
+ [ 5, 0]]), tensor([[ 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 5, 8, 8, 9,
188
+ 9, 10, 10, 11, 11, 12, 12, 13, 13, 14, 14, 15, 15, 16, 16, 17, 16, 18,
189
+ 14, 19, 9, 20, 20, 21, 21, 22, 22, 23, 23, 24, 24, 25, 25, 26, 26, 27,
190
+ 26, 28, 24, 29, 8, 30, 30, 31, 31, 32, 32, 33, 33, 34, 33, 35, 32, 36,
191
+ 36, 37, 37, 38, 38, 39, 38, 40, 37, 41, 41, 42, 42, 43, 43, 44, 43, 45,
192
+ 30, 2, 42, 31, 18, 10, 28, 20, 19, 10, 29, 20, 17, 12, 27, 22],
193
+ [ 1, 0, 2, 1, 3, 2, 4, 3, 5, 4, 6, 5, 7, 6, 8, 5, 9, 8,
194
+ 10, 9, 11, 10, 12, 11, 13, 12, 14, 13, 15, 14, 16, 15, 17, 16, 18, 16,
195
+ 19, 14, 20, 9, 21, 20, 22, 21, 23, 22, 24, 23, 25, 24, 26, 25, 27, 26,
196
+ 28, 26, 29, 24, 30, 8, 31, 30, 32, 31, 33, 32, 34, 33, 35, 33, 36, 32,
197
+ 37, 36, 38, 37, 39, 38, 40, 38, 41, 37, 42, 41, 43, 42, 44, 43, 45, 43,
198
+ 2, 30, 31, 42, 10, 18, 20, 28, 10, 19, 20, 29, 12, 17, 22, 27]]), tensor([[0, 0],
199
+ [0, 0],
200
+ [0, 0],
201
+ [0, 0],
202
+ [3, 0],
203
+ [3, 0],
204
+ [3, 0],
205
+ [3, 0],
206
+ [3, 0],
207
+ [3, 0],
208
+ [0, 0],
209
+ [0, 0],
210
+ [0, 0],
211
+ [0, 0],
212
+ [3, 0],
213
+ [3, 0],
214
+ [0, 0],
215
+ [0, 0],
216
+ [0, 0],
217
+ [0, 0],
218
+ [0, 0],
219
+ [0, 0],
220
+ [0, 0],
221
+ [0, 0],
222
+ [0, 0],
223
+ [0, 0],
224
+ [0, 0],
225
+ [0, 0],
226
+ [0, 0],
227
+ [0, 0],
228
+ [0, 0],
229
+ [0, 0],
230
+ [0, 0],
231
+ [0, 0],
232
+ [0, 0],
233
+ [0, 0],
234
+ [0, 0],
235
+ [0, 0],
236
+ [0, 0],
237
+ [0, 0],
238
+ [0, 0],
239
+ [0, 0],
240
+ [0, 0],
241
+ [0, 0],
242
+ [0, 0],
243
+ [0, 0],
244
+ [0, 0],
245
+ [0, 0],
246
+ [0, 0],
247
+ [0, 0],
248
+ [0, 0],
249
+ [0, 0],
250
+ [0, 0],
251
+ [0, 0],
252
+ [0, 0],
253
+ [0, 0],
254
+ [0, 0],
255
+ [0, 0],
256
+ [3, 0],
257
+ [3, 0],
258
+ [0, 0],
259
+ [0, 0],
260
+ [3, 0],
261
+ [3, 0],
262
+ [0, 0],
263
+ [0, 0],
264
+ [0, 0],
265
+ [0, 0],
266
+ [0, 0],
267
+ [0, 0],
268
+ [3, 0],
269
+ [3, 0],
270
+ [3, 0],
271
+ [3, 0],
272
+ [0, 0],
273
+ [0, 0],
274
+ [0, 0],
275
+ [0, 0],
276
+ [0, 0],
277
+ [0, 0],
278
+ [3, 0],
279
+ [3, 0],
280
+ [3, 0],
281
+ [3, 0],
282
+ [0, 0],
283
+ [0, 0],
284
+ [0, 0],
285
+ [0, 0],
286
+ [0, 0],
287
+ [0, 0],
288
+ [3, 0],
289
+ [3, 0],
290
+ [3, 0],
291
+ [3, 0],
292
+ [0, 0],
293
+ [0, 0],
294
+ [0, 0],
295
+ [0, 0],
296
+ [0, 0],
297
+ [0, 0],
298
+ [0, 0],
299
+ [0, 0],
300
+ [0, 0],
301
+ [0, 0],
302
+ [0, 0],
303
+ [0, 0]])), (tensor([[ 5, 0],
304
+ [ 5, 0],
305
+ [ 6, 0],
306
+ [14, 0],
307
+ [ 6, 0],
308
+ [14, 0],
309
+ [ 6, 0],
310
+ [ 5, 0],
311
+ [ 5, 0],
312
+ [ 6, 0],
313
+ [ 5, 0],
314
+ [ 5, 0],
315
+ [ 6, 0],
316
+ [ 5, 0],
317
+ [ 5, 0],
318
+ [ 6, 0],
319
+ [ 5, 0],
320
+ [ 5, 0],
321
+ [ 6, 0],
322
+ [ 5, 0],
323
+ [ 5, 0]]), tensor([[ 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 6, 8, 5, 9,
324
+ 9, 10, 9, 11, 5, 12, 12, 13, 12, 14, 3, 15, 15, 16, 15, 17, 3, 18,
325
+ 18, 19, 18, 20],
326
+ [ 1, 0, 2, 1, 3, 2, 4, 3, 5, 4, 6, 5, 7, 6, 8, 6, 9, 5,
327
+ 10, 9, 11, 9, 12, 5, 13, 12, 14, 12, 15, 3, 16, 15, 17, 15, 18, 3,
328
+ 19, 18, 20, 18]]), tensor([[0, 0],
329
+ [0, 0],
330
+ [0, 0],
331
+ [0, 0],
332
+ [1, 0],
333
+ [1, 0],
334
+ [0, 0],
335
+ [0, 0],
336
+ [1, 0],
337
+ [1, 0],
338
+ [0, 0],
339
+ [0, 0],
340
+ [0, 0],
341
+ [0, 0],
342
+ [0, 0],
343
+ [0, 0],
344
+ [0, 0],
345
+ [0, 0],
346
+ [0, 0],
347
+ [0, 0],
348
+ [0, 0],
349
+ [0, 0],
350
+ [0, 0],
351
+ [0, 0],
352
+ [0, 0],
353
+ [0, 0],
354
+ [0, 0],
355
+ [0, 0],
356
+ [0, 0],
357
+ [0, 0],
358
+ [0, 0],
359
+ [0, 0],
360
+ [0, 0],
361
+ [0, 0],
362
+ [0, 0],
363
+ [0, 0],
364
+ [0, 0],
365
+ [0, 0],
366
+ [0, 0],
367
+ [0, 0]])), (tensor([[5, 0],
368
+ [5, 0],
369
+ [5, 0],
370
+ [5, 0],
371
+ [6, 0],
372
+ [7, 0]]), tensor([[0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 1],
373
+ [1, 0, 2, 1, 3, 2, 4, 3, 5, 4, 1, 5]]), tensor([[0, 0],
374
+ [0, 0],
375
+ [3, 0],
376
+ [3, 0],
377
+ [3, 0],
378
+ [3, 0],
379
+ [3, 0],
380
+ [3, 0],
381
+ [3, 0],
382
+ [3, 0],
383
+ [3, 0],
384
+ [3, 0]])), (tensor([[5, 0],
385
+ [5, 0],
386
+ [5, 0],
387
+ [5, 0],
388
+ [5, 0],
389
+ [6, 0],
390
+ [5, 0],
391
+ [5, 0],
392
+ [5, 0],
393
+ [5, 0],
394
+ [6, 0],
395
+ [5, 0],
396
+ [5, 0],
397
+ [5, 0]]), tensor([[ 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9,
398
+ 9, 10, 10, 11, 4, 12, 12, 13, 13, 1, 11, 6],
399
+ [ 1, 0, 2, 1, 3, 2, 4, 3, 5, 4, 6, 5, 7, 6, 8, 7, 9, 8,
400
+ 10, 9, 11, 10, 12, 4, 13, 12, 1, 13, 6, 11]]), tensor([[0, 0],
401
+ [0, 0],
402
+ [3, 0],
403
+ [3, 0],
404
+ [3, 0],
405
+ [3, 0],
406
+ [3, 0],
407
+ [3, 0],
408
+ [0, 0],
409
+ [0, 0],
410
+ [0, 0],
411
+ [0, 0],
412
+ [3, 0],
413
+ [3, 0],
414
+ [3, 0],
415
+ [3, 0],
416
+ [3, 0],
417
+ [3, 0],
418
+ [3, 0],
419
+ [3, 0],
420
+ [3, 0],
421
+ [3, 0],
422
+ [3, 0],
423
+ [3, 0],
424
+ [3, 0],
425
+ [3, 0],
426
+ [3, 0],
427
+ [3, 0],
428
+ [3, 0],
429
+ [3, 0]]))], 'input_ids': tensor([ 1, 518, 25580, 29962, 3532, 14816, 29903, 6778, 13, 3492,
430
+ 526, 263, 8950, 391, 29889, 2567, 366, 526, 2183, 263,
431
+ 19848, 6306, 29889, 3529, 8500, 278, 1950, 337, 351, 1237,
432
+ 310, 278, 19848, 29889, 450, 19848, 6306, 756, 278, 1494,
433
+ 3402, 29901, 13, 28956, 13, 8423, 424, 29896, 29889, 8423,
434
+ 424, 29906, 29889, 2023, 869, 8423, 424, 29940, 6778, 4704,
435
+ 13, 28956, 13, 1576, 736, 995, 881, 367, 297, 3464,
436
+ 310, 29871, 29900, 29899, 29896, 29889, 450, 6133, 278, 995,
437
+ 29892, 278, 901, 5517, 278, 19848, 338, 304, 6403, 29889,
438
+ 29871, 13, 4806, 3867, 278, 3829, 310, 278, 337, 7387,
439
+ 29889, 13, 29966, 829, 14816, 29903, 6778, 13, 13, -3996,
440
+ -3996, -3996, -3996, -3996, -3996, -3996, 869, -3996, -3996, -3996,
441
+ -3996, -3996, -3996, -3996, -3996, 869, -3996, -3996, -3996, -3996,
442
+ -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996,
443
+ -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, 869, -3996,
444
+ -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996,
445
+ -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996,
446
+ -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996,
447
+ -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996,
448
+ -3996, -3996, -3996, -3996, -3996, 869, -3996, -3996, -3996, -3996,
449
+ -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996,
450
+ -3996, -3996, -3996, -3996, -3996, -3996, -3996, 869, -3996, -3996,
451
+ -3996, -3996, -3996, -3996, 5099, -3996, -3996, -3996, -3996, -3996,
452
+ -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, -3996, 29871,
453
+ 5293, 278, 22233, 19848, 2472, 29892, 825, 338, 278, 11959,
454
+ 310, 278, 19848, 29915, 29879, 7709, 29973, 518, 29914, 25580,
455
+ 29962, 259, 29900, 29889, 29900, 29941, 29953, 29947, 29871, 2]), 'labels': tensor([ 1, -100, -100, -100, -100, -100, -100, -100, -100, -100,
456
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
457
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
458
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
459
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
460
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
461
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
462
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
463
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
464
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
465
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
466
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
467
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
468
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
469
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
470
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
471
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
472
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
473
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
474
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
475
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
476
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
477
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
478
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
479
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
480
+ -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,
481
+ -100, 259, 29900, 29889, 29900, 29941, 29953, 29947, 29871, 2])}
482
+ ```
483
+
484
+ ### Training Device(s)
485
+
486
+ ```
487
+ name, pci.bus_id, vbios_version
488
+ NVIDIA RTX A6000, 00000000:01:00.0, 94.02.5C.00.02
489
+ NVIDIA RTX A6000, 00000000:25:00.0, 94.02.5C.00.02
490
+ NVIDIA RTX A6000, 00000000:41:00.0, 94.02.5C.00.02
491
+ NVIDIA RTX A6000, 00000000:61:00.0, 94.02.5C.00.02
492
+ NVIDIA RTX A6000, 00000000:81:00.0, 94.02.5C.00.02
493
+ NVIDIA RTX A6000, 00000000:A1:00.0, 94.02.5C.00.02
494
+ NVIDIA RTX A6000, 00000000:C1:00.0, 94.02.5C.00.02
495
+ NVIDIA RTX A6000, 00000000:E1:00.0, 94.02.5C.00.02
496
+ ```
497
+
498
+
499
+ ### Model
500
+
501
+ ```
502
+ LlamaLMMForCausalLM.model =
503
+
504
+ LlamaLMMForCausalLM(
505
+ (model): LlamaLMMModel(
506
+ (embed_tokens): Embedding(32000, 4096, padding_idx=0)
507
+ (layers): ModuleList(
508
+ (0-31): 32 x LlamaDecoderLayer(
509
+ (self_attn): LlamaSdpaAttention(
510
+ (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
511
+ (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
512
+ (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
513
+ (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
514
+ (rotary_emb): LlamaRotaryEmbedding()
515
+ )
516
+ (mlp): LlamaMLP(
517
+ (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
518
+ (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
519
+ (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
520
+ (act_fn): SiLU()
521
+ )
522
+ (input_layernorm): LlamaRMSNorm()
523
+ (post_attention_layernorm): LlamaRMSNorm()
524
+ )
525
+ )
526
+ (norm): LlamaRMSNorm()
527
+ (molecule_2d_lmm_projector): _MLPVectorProjector(
528
+ (mlp): Sequential(
529
+ (0): Linear(in_features=300, out_features=4096, bias=True)
530
+ (1): GELU(approximate='none')
531
+ (2): Linear(in_features=4096, out_features=4096, bias=True)
532
+ )
533
+ )
534
+ )
535
+ (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
536
+ )
537
+ ```
538
+
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "checkpoints/stage2/llava-moleculestm-vicuna-7b-v1.5-pretrain_all",
3
+ "architectures": [
4
+ "LlamaLMMForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "modalities": [
16
+ "molecule_2d"
17
+ ],
18
+ "modality_builder": "molecule_2d",
19
+ "model_cls": "LlamaLMMForCausalLM",
20
+ "model_type": "llama-lmm",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "pad_token_id": 0,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": null,
28
+ "rope_theta": 10000.0,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.39.1",
32
+ "use_cache": true,
33
+ "vocab_size": 32000
34
+ }
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
+ "pad_token_id": 0,
6
+ "transformers_version": "4.39.1"
7
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,302 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13512859648
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.molecule_2d_lmm_projector.mlp.0.bias": "model-00003-of-00003.safetensors",
297
+ "model.molecule_2d_lmm_projector.mlp.0.weight": "model-00003-of-00003.safetensors",
298
+ "model.molecule_2d_lmm_projector.mlp.2.bias": "model-00003-of-00003.safetensors",
299
+ "model.molecule_2d_lmm_projector.mlp.2.weight": "model-00003-of-00003.safetensors",
300
+ "model.norm.weight": "model-00003-of-00003.safetensors"
301
+ }
302
+ }
model_named_parameters.txt ADDED
@@ -0,0 +1,295 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model.embed_tokens.weight torch.Size([32000, 4096]) True
2
+ model.layers.0.self_attn.q_proj.weight torch.Size([4096, 4096]) True
3
+ model.layers.0.self_attn.k_proj.weight torch.Size([4096, 4096]) True
4
+ model.layers.0.self_attn.v_proj.weight torch.Size([4096, 4096]) True
5
+ model.layers.0.self_attn.o_proj.weight torch.Size([4096, 4096]) True
6
+ model.layers.0.mlp.gate_proj.weight torch.Size([11008, 4096]) True
7
+ model.layers.0.mlp.up_proj.weight torch.Size([11008, 4096]) True
8
+ model.layers.0.mlp.down_proj.weight torch.Size([4096, 11008]) True
9
+ model.layers.0.input_layernorm.weight torch.Size([4096]) True
10
+ model.layers.0.post_attention_layernorm.weight torch.Size([4096]) True
11
+ model.layers.1.self_attn.q_proj.weight torch.Size([4096, 4096]) True
12
+ model.layers.1.self_attn.k_proj.weight torch.Size([4096, 4096]) True
13
+ model.layers.1.self_attn.v_proj.weight torch.Size([4096, 4096]) True
14
+ model.layers.1.self_attn.o_proj.weight torch.Size([4096, 4096]) True
15
+ model.layers.1.mlp.gate_proj.weight torch.Size([11008, 4096]) True
16
+ model.layers.1.mlp.up_proj.weight torch.Size([11008, 4096]) True
17
+ model.layers.1.mlp.down_proj.weight torch.Size([4096, 11008]) True
18
+ model.layers.1.input_layernorm.weight torch.Size([4096]) True
19
+ model.layers.1.post_attention_layernorm.weight torch.Size([4096]) True
20
+ model.layers.2.self_attn.q_proj.weight torch.Size([4096, 4096]) True
21
+ model.layers.2.self_attn.k_proj.weight torch.Size([4096, 4096]) True
22
+ model.layers.2.self_attn.v_proj.weight torch.Size([4096, 4096]) True
23
+ model.layers.2.self_attn.o_proj.weight torch.Size([4096, 4096]) True
24
+ model.layers.2.mlp.gate_proj.weight torch.Size([11008, 4096]) True
25
+ model.layers.2.mlp.up_proj.weight torch.Size([11008, 4096]) True
26
+ model.layers.2.mlp.down_proj.weight torch.Size([4096, 11008]) True
27
+ model.layers.2.input_layernorm.weight torch.Size([4096]) True
28
+ model.layers.2.post_attention_layernorm.weight torch.Size([4096]) True
29
+ model.layers.3.self_attn.q_proj.weight torch.Size([4096, 4096]) True
30
+ model.layers.3.self_attn.k_proj.weight torch.Size([4096, 4096]) True
31
+ model.layers.3.self_attn.v_proj.weight torch.Size([4096, 4096]) True
32
+ model.layers.3.self_attn.o_proj.weight torch.Size([4096, 4096]) True
33
+ model.layers.3.mlp.gate_proj.weight torch.Size([11008, 4096]) True
34
+ model.layers.3.mlp.up_proj.weight torch.Size([11008, 4096]) True
35
+ model.layers.3.mlp.down_proj.weight torch.Size([4096, 11008]) True
36
+ model.layers.3.input_layernorm.weight torch.Size([4096]) True
37
+ model.layers.3.post_attention_layernorm.weight torch.Size([4096]) True
38
+ model.layers.4.self_attn.q_proj.weight torch.Size([4096, 4096]) True
39
+ model.layers.4.self_attn.k_proj.weight torch.Size([4096, 4096]) True
40
+ model.layers.4.self_attn.v_proj.weight torch.Size([4096, 4096]) True
41
+ model.layers.4.self_attn.o_proj.weight torch.Size([4096, 4096]) True
42
+ model.layers.4.mlp.gate_proj.weight torch.Size([11008, 4096]) True
43
+ model.layers.4.mlp.up_proj.weight torch.Size([11008, 4096]) True
44
+ model.layers.4.mlp.down_proj.weight torch.Size([4096, 11008]) True
45
+ model.layers.4.input_layernorm.weight torch.Size([4096]) True
46
+ model.layers.4.post_attention_layernorm.weight torch.Size([4096]) True
47
+ model.layers.5.self_attn.q_proj.weight torch.Size([4096, 4096]) True
48
+ model.layers.5.self_attn.k_proj.weight torch.Size([4096, 4096]) True
49
+ model.layers.5.self_attn.v_proj.weight torch.Size([4096, 4096]) True
50
+ model.layers.5.self_attn.o_proj.weight torch.Size([4096, 4096]) True
51
+ model.layers.5.mlp.gate_proj.weight torch.Size([11008, 4096]) True
52
+ model.layers.5.mlp.up_proj.weight torch.Size([11008, 4096]) True
53
+ model.layers.5.mlp.down_proj.weight torch.Size([4096, 11008]) True
54
+ model.layers.5.input_layernorm.weight torch.Size([4096]) True
55
+ model.layers.5.post_attention_layernorm.weight torch.Size([4096]) True
56
+ model.layers.6.self_attn.q_proj.weight torch.Size([4096, 4096]) True
57
+ model.layers.6.self_attn.k_proj.weight torch.Size([4096, 4096]) True
58
+ model.layers.6.self_attn.v_proj.weight torch.Size([4096, 4096]) True
59
+ model.layers.6.self_attn.o_proj.weight torch.Size([4096, 4096]) True
60
+ model.layers.6.mlp.gate_proj.weight torch.Size([11008, 4096]) True
61
+ model.layers.6.mlp.up_proj.weight torch.Size([11008, 4096]) True
62
+ model.layers.6.mlp.down_proj.weight torch.Size([4096, 11008]) True
63
+ model.layers.6.input_layernorm.weight torch.Size([4096]) True
64
+ model.layers.6.post_attention_layernorm.weight torch.Size([4096]) True
65
+ model.layers.7.self_attn.q_proj.weight torch.Size([4096, 4096]) True
66
+ model.layers.7.self_attn.k_proj.weight torch.Size([4096, 4096]) True
67
+ model.layers.7.self_attn.v_proj.weight torch.Size([4096, 4096]) True
68
+ model.layers.7.self_attn.o_proj.weight torch.Size([4096, 4096]) True
69
+ model.layers.7.mlp.gate_proj.weight torch.Size([11008, 4096]) True
70
+ model.layers.7.mlp.up_proj.weight torch.Size([11008, 4096]) True
71
+ model.layers.7.mlp.down_proj.weight torch.Size([4096, 11008]) True
72
+ model.layers.7.input_layernorm.weight torch.Size([4096]) True
73
+ model.layers.7.post_attention_layernorm.weight torch.Size([4096]) True
74
+ model.layers.8.self_attn.q_proj.weight torch.Size([4096, 4096]) True
75
+ model.layers.8.self_attn.k_proj.weight torch.Size([4096, 4096]) True
76
+ model.layers.8.self_attn.v_proj.weight torch.Size([4096, 4096]) True
77
+ model.layers.8.self_attn.o_proj.weight torch.Size([4096, 4096]) True
78
+ model.layers.8.mlp.gate_proj.weight torch.Size([11008, 4096]) True
79
+ model.layers.8.mlp.up_proj.weight torch.Size([11008, 4096]) True
80
+ model.layers.8.mlp.down_proj.weight torch.Size([4096, 11008]) True
81
+ model.layers.8.input_layernorm.weight torch.Size([4096]) True
82
+ model.layers.8.post_attention_layernorm.weight torch.Size([4096]) True
83
+ model.layers.9.self_attn.q_proj.weight torch.Size([4096, 4096]) True
84
+ model.layers.9.self_attn.k_proj.weight torch.Size([4096, 4096]) True
85
+ model.layers.9.self_attn.v_proj.weight torch.Size([4096, 4096]) True
86
+ model.layers.9.self_attn.o_proj.weight torch.Size([4096, 4096]) True
87
+ model.layers.9.mlp.gate_proj.weight torch.Size([11008, 4096]) True
88
+ model.layers.9.mlp.up_proj.weight torch.Size([11008, 4096]) True
89
+ model.layers.9.mlp.down_proj.weight torch.Size([4096, 11008]) True
90
+ model.layers.9.input_layernorm.weight torch.Size([4096]) True
91
+ model.layers.9.post_attention_layernorm.weight torch.Size([4096]) True
92
+ model.layers.10.self_attn.q_proj.weight torch.Size([4096, 4096]) True
93
+ model.layers.10.self_attn.k_proj.weight torch.Size([4096, 4096]) True
94
+ model.layers.10.self_attn.v_proj.weight torch.Size([4096, 4096]) True
95
+ model.layers.10.self_attn.o_proj.weight torch.Size([4096, 4096]) True
96
+ model.layers.10.mlp.gate_proj.weight torch.Size([11008, 4096]) True
97
+ model.layers.10.mlp.up_proj.weight torch.Size([11008, 4096]) True
98
+ model.layers.10.mlp.down_proj.weight torch.Size([4096, 11008]) True
99
+ model.layers.10.input_layernorm.weight torch.Size([4096]) True
100
+ model.layers.10.post_attention_layernorm.weight torch.Size([4096]) True
101
+ model.layers.11.self_attn.q_proj.weight torch.Size([4096, 4096]) True
102
+ model.layers.11.self_attn.k_proj.weight torch.Size([4096, 4096]) True
103
+ model.layers.11.self_attn.v_proj.weight torch.Size([4096, 4096]) True
104
+ model.layers.11.self_attn.o_proj.weight torch.Size([4096, 4096]) True
105
+ model.layers.11.mlp.gate_proj.weight torch.Size([11008, 4096]) True
106
+ model.layers.11.mlp.up_proj.weight torch.Size([11008, 4096]) True
107
+ model.layers.11.mlp.down_proj.weight torch.Size([4096, 11008]) True
108
+ model.layers.11.input_layernorm.weight torch.Size([4096]) True
109
+ model.layers.11.post_attention_layernorm.weight torch.Size([4096]) True
110
+ model.layers.12.self_attn.q_proj.weight torch.Size([4096, 4096]) True
111
+ model.layers.12.self_attn.k_proj.weight torch.Size([4096, 4096]) True
112
+ model.layers.12.self_attn.v_proj.weight torch.Size([4096, 4096]) True
113
+ model.layers.12.self_attn.o_proj.weight torch.Size([4096, 4096]) True
114
+ model.layers.12.mlp.gate_proj.weight torch.Size([11008, 4096]) True
115
+ model.layers.12.mlp.up_proj.weight torch.Size([11008, 4096]) True
116
+ model.layers.12.mlp.down_proj.weight torch.Size([4096, 11008]) True
117
+ model.layers.12.input_layernorm.weight torch.Size([4096]) True
118
+ model.layers.12.post_attention_layernorm.weight torch.Size([4096]) True
119
+ model.layers.13.self_attn.q_proj.weight torch.Size([4096, 4096]) True
120
+ model.layers.13.self_attn.k_proj.weight torch.Size([4096, 4096]) True
121
+ model.layers.13.self_attn.v_proj.weight torch.Size([4096, 4096]) True
122
+ model.layers.13.self_attn.o_proj.weight torch.Size([4096, 4096]) True
123
+ model.layers.13.mlp.gate_proj.weight torch.Size([11008, 4096]) True
124
+ model.layers.13.mlp.up_proj.weight torch.Size([11008, 4096]) True
125
+ model.layers.13.mlp.down_proj.weight torch.Size([4096, 11008]) True
126
+ model.layers.13.input_layernorm.weight torch.Size([4096]) True
127
+ model.layers.13.post_attention_layernorm.weight torch.Size([4096]) True
128
+ model.layers.14.self_attn.q_proj.weight torch.Size([4096, 4096]) True
129
+ model.layers.14.self_attn.k_proj.weight torch.Size([4096, 4096]) True
130
+ model.layers.14.self_attn.v_proj.weight torch.Size([4096, 4096]) True
131
+ model.layers.14.self_attn.o_proj.weight torch.Size([4096, 4096]) True
132
+ model.layers.14.mlp.gate_proj.weight torch.Size([11008, 4096]) True
133
+ model.layers.14.mlp.up_proj.weight torch.Size([11008, 4096]) True
134
+ model.layers.14.mlp.down_proj.weight torch.Size([4096, 11008]) True
135
+ model.layers.14.input_layernorm.weight torch.Size([4096]) True
136
+ model.layers.14.post_attention_layernorm.weight torch.Size([4096]) True
137
+ model.layers.15.self_attn.q_proj.weight torch.Size([4096, 4096]) True
138
+ model.layers.15.self_attn.k_proj.weight torch.Size([4096, 4096]) True
139
+ model.layers.15.self_attn.v_proj.weight torch.Size([4096, 4096]) True
140
+ model.layers.15.self_attn.o_proj.weight torch.Size([4096, 4096]) True
141
+ model.layers.15.mlp.gate_proj.weight torch.Size([11008, 4096]) True
142
+ model.layers.15.mlp.up_proj.weight torch.Size([11008, 4096]) True
143
+ model.layers.15.mlp.down_proj.weight torch.Size([4096, 11008]) True
144
+ model.layers.15.input_layernorm.weight torch.Size([4096]) True
145
+ model.layers.15.post_attention_layernorm.weight torch.Size([4096]) True
146
+ model.layers.16.self_attn.q_proj.weight torch.Size([4096, 4096]) True
147
+ model.layers.16.self_attn.k_proj.weight torch.Size([4096, 4096]) True
148
+ model.layers.16.self_attn.v_proj.weight torch.Size([4096, 4096]) True
149
+ model.layers.16.self_attn.o_proj.weight torch.Size([4096, 4096]) True
150
+ model.layers.16.mlp.gate_proj.weight torch.Size([11008, 4096]) True
151
+ model.layers.16.mlp.up_proj.weight torch.Size([11008, 4096]) True
152
+ model.layers.16.mlp.down_proj.weight torch.Size([4096, 11008]) True
153
+ model.layers.16.input_layernorm.weight torch.Size([4096]) True
154
+ model.layers.16.post_attention_layernorm.weight torch.Size([4096]) True
155
+ model.layers.17.self_attn.q_proj.weight torch.Size([4096, 4096]) True
156
+ model.layers.17.self_attn.k_proj.weight torch.Size([4096, 4096]) True
157
+ model.layers.17.self_attn.v_proj.weight torch.Size([4096, 4096]) True
158
+ model.layers.17.self_attn.o_proj.weight torch.Size([4096, 4096]) True
159
+ model.layers.17.mlp.gate_proj.weight torch.Size([11008, 4096]) True
160
+ model.layers.17.mlp.up_proj.weight torch.Size([11008, 4096]) True
161
+ model.layers.17.mlp.down_proj.weight torch.Size([4096, 11008]) True
162
+ model.layers.17.input_layernorm.weight torch.Size([4096]) True
163
+ model.layers.17.post_attention_layernorm.weight torch.Size([4096]) True
164
+ model.layers.18.self_attn.q_proj.weight torch.Size([4096, 4096]) True
165
+ model.layers.18.self_attn.k_proj.weight torch.Size([4096, 4096]) True
166
+ model.layers.18.self_attn.v_proj.weight torch.Size([4096, 4096]) True
167
+ model.layers.18.self_attn.o_proj.weight torch.Size([4096, 4096]) True
168
+ model.layers.18.mlp.gate_proj.weight torch.Size([11008, 4096]) True
169
+ model.layers.18.mlp.up_proj.weight torch.Size([11008, 4096]) True
170
+ model.layers.18.mlp.down_proj.weight torch.Size([4096, 11008]) True
171
+ model.layers.18.input_layernorm.weight torch.Size([4096]) True
172
+ model.layers.18.post_attention_layernorm.weight torch.Size([4096]) True
173
+ model.layers.19.self_attn.q_proj.weight torch.Size([4096, 4096]) True
174
+ model.layers.19.self_attn.k_proj.weight torch.Size([4096, 4096]) True
175
+ model.layers.19.self_attn.v_proj.weight torch.Size([4096, 4096]) True
176
+ model.layers.19.self_attn.o_proj.weight torch.Size([4096, 4096]) True
177
+ model.layers.19.mlp.gate_proj.weight torch.Size([11008, 4096]) True
178
+ model.layers.19.mlp.up_proj.weight torch.Size([11008, 4096]) True
179
+ model.layers.19.mlp.down_proj.weight torch.Size([4096, 11008]) True
180
+ model.layers.19.input_layernorm.weight torch.Size([4096]) True
181
+ model.layers.19.post_attention_layernorm.weight torch.Size([4096]) True
182
+ model.layers.20.self_attn.q_proj.weight torch.Size([4096, 4096]) True
183
+ model.layers.20.self_attn.k_proj.weight torch.Size([4096, 4096]) True
184
+ model.layers.20.self_attn.v_proj.weight torch.Size([4096, 4096]) True
185
+ model.layers.20.self_attn.o_proj.weight torch.Size([4096, 4096]) True
186
+ model.layers.20.mlp.gate_proj.weight torch.Size([11008, 4096]) True
187
+ model.layers.20.mlp.up_proj.weight torch.Size([11008, 4096]) True
188
+ model.layers.20.mlp.down_proj.weight torch.Size([4096, 11008]) True
189
+ model.layers.20.input_layernorm.weight torch.Size([4096]) True
190
+ model.layers.20.post_attention_layernorm.weight torch.Size([4096]) True
191
+ model.layers.21.self_attn.q_proj.weight torch.Size([4096, 4096]) True
192
+ model.layers.21.self_attn.k_proj.weight torch.Size([4096, 4096]) True
193
+ model.layers.21.self_attn.v_proj.weight torch.Size([4096, 4096]) True
194
+ model.layers.21.self_attn.o_proj.weight torch.Size([4096, 4096]) True
195
+ model.layers.21.mlp.gate_proj.weight torch.Size([11008, 4096]) True
196
+ model.layers.21.mlp.up_proj.weight torch.Size([11008, 4096]) True
197
+ model.layers.21.mlp.down_proj.weight torch.Size([4096, 11008]) True
198
+ model.layers.21.input_layernorm.weight torch.Size([4096]) True
199
+ model.layers.21.post_attention_layernorm.weight torch.Size([4096]) True
200
+ model.layers.22.self_attn.q_proj.weight torch.Size([4096, 4096]) True
201
+ model.layers.22.self_attn.k_proj.weight torch.Size([4096, 4096]) True
202
+ model.layers.22.self_attn.v_proj.weight torch.Size([4096, 4096]) True
203
+ model.layers.22.self_attn.o_proj.weight torch.Size([4096, 4096]) True
204
+ model.layers.22.mlp.gate_proj.weight torch.Size([11008, 4096]) True
205
+ model.layers.22.mlp.up_proj.weight torch.Size([11008, 4096]) True
206
+ model.layers.22.mlp.down_proj.weight torch.Size([4096, 11008]) True
207
+ model.layers.22.input_layernorm.weight torch.Size([4096]) True
208
+ model.layers.22.post_attention_layernorm.weight torch.Size([4096]) True
209
+ model.layers.23.self_attn.q_proj.weight torch.Size([4096, 4096]) True
210
+ model.layers.23.self_attn.k_proj.weight torch.Size([4096, 4096]) True
211
+ model.layers.23.self_attn.v_proj.weight torch.Size([4096, 4096]) True
212
+ model.layers.23.self_attn.o_proj.weight torch.Size([4096, 4096]) True
213
+ model.layers.23.mlp.gate_proj.weight torch.Size([11008, 4096]) True
214
+ model.layers.23.mlp.up_proj.weight torch.Size([11008, 4096]) True
215
+ model.layers.23.mlp.down_proj.weight torch.Size([4096, 11008]) True
216
+ model.layers.23.input_layernorm.weight torch.Size([4096]) True
217
+ model.layers.23.post_attention_layernorm.weight torch.Size([4096]) True
218
+ model.layers.24.self_attn.q_proj.weight torch.Size([4096, 4096]) True
219
+ model.layers.24.self_attn.k_proj.weight torch.Size([4096, 4096]) True
220
+ model.layers.24.self_attn.v_proj.weight torch.Size([4096, 4096]) True
221
+ model.layers.24.self_attn.o_proj.weight torch.Size([4096, 4096]) True
222
+ model.layers.24.mlp.gate_proj.weight torch.Size([11008, 4096]) True
223
+ model.layers.24.mlp.up_proj.weight torch.Size([11008, 4096]) True
224
+ model.layers.24.mlp.down_proj.weight torch.Size([4096, 11008]) True
225
+ model.layers.24.input_layernorm.weight torch.Size([4096]) True
226
+ model.layers.24.post_attention_layernorm.weight torch.Size([4096]) True
227
+ model.layers.25.self_attn.q_proj.weight torch.Size([4096, 4096]) True
228
+ model.layers.25.self_attn.k_proj.weight torch.Size([4096, 4096]) True
229
+ model.layers.25.self_attn.v_proj.weight torch.Size([4096, 4096]) True
230
+ model.layers.25.self_attn.o_proj.weight torch.Size([4096, 4096]) True
231
+ model.layers.25.mlp.gate_proj.weight torch.Size([11008, 4096]) True
232
+ model.layers.25.mlp.up_proj.weight torch.Size([11008, 4096]) True
233
+ model.layers.25.mlp.down_proj.weight torch.Size([4096, 11008]) True
234
+ model.layers.25.input_layernorm.weight torch.Size([4096]) True
235
+ model.layers.25.post_attention_layernorm.weight torch.Size([4096]) True
236
+ model.layers.26.self_attn.q_proj.weight torch.Size([4096, 4096]) True
237
+ model.layers.26.self_attn.k_proj.weight torch.Size([4096, 4096]) True
238
+ model.layers.26.self_attn.v_proj.weight torch.Size([4096, 4096]) True
239
+ model.layers.26.self_attn.o_proj.weight torch.Size([4096, 4096]) True
240
+ model.layers.26.mlp.gate_proj.weight torch.Size([11008, 4096]) True
241
+ model.layers.26.mlp.up_proj.weight torch.Size([11008, 4096]) True
242
+ model.layers.26.mlp.down_proj.weight torch.Size([4096, 11008]) True
243
+ model.layers.26.input_layernorm.weight torch.Size([4096]) True
244
+ model.layers.26.post_attention_layernorm.weight torch.Size([4096]) True
245
+ model.layers.27.self_attn.q_proj.weight torch.Size([4096, 4096]) True
246
+ model.layers.27.self_attn.k_proj.weight torch.Size([4096, 4096]) True
247
+ model.layers.27.self_attn.v_proj.weight torch.Size([4096, 4096]) True
248
+ model.layers.27.self_attn.o_proj.weight torch.Size([4096, 4096]) True
249
+ model.layers.27.mlp.gate_proj.weight torch.Size([11008, 4096]) True
250
+ model.layers.27.mlp.up_proj.weight torch.Size([11008, 4096]) True
251
+ model.layers.27.mlp.down_proj.weight torch.Size([4096, 11008]) True
252
+ model.layers.27.input_layernorm.weight torch.Size([4096]) True
253
+ model.layers.27.post_attention_layernorm.weight torch.Size([4096]) True
254
+ model.layers.28.self_attn.q_proj.weight torch.Size([4096, 4096]) True
255
+ model.layers.28.self_attn.k_proj.weight torch.Size([4096, 4096]) True
256
+ model.layers.28.self_attn.v_proj.weight torch.Size([4096, 4096]) True
257
+ model.layers.28.self_attn.o_proj.weight torch.Size([4096, 4096]) True
258
+ model.layers.28.mlp.gate_proj.weight torch.Size([11008, 4096]) True
259
+ model.layers.28.mlp.up_proj.weight torch.Size([11008, 4096]) True
260
+ model.layers.28.mlp.down_proj.weight torch.Size([4096, 11008]) True
261
+ model.layers.28.input_layernorm.weight torch.Size([4096]) True
262
+ model.layers.28.post_attention_layernorm.weight torch.Size([4096]) True
263
+ model.layers.29.self_attn.q_proj.weight torch.Size([4096, 4096]) True
264
+ model.layers.29.self_attn.k_proj.weight torch.Size([4096, 4096]) True
265
+ model.layers.29.self_attn.v_proj.weight torch.Size([4096, 4096]) True
266
+ model.layers.29.self_attn.o_proj.weight torch.Size([4096, 4096]) True
267
+ model.layers.29.mlp.gate_proj.weight torch.Size([11008, 4096]) True
268
+ model.layers.29.mlp.up_proj.weight torch.Size([11008, 4096]) True
269
+ model.layers.29.mlp.down_proj.weight torch.Size([4096, 11008]) True
270
+ model.layers.29.input_layernorm.weight torch.Size([4096]) True
271
+ model.layers.29.post_attention_layernorm.weight torch.Size([4096]) True
272
+ model.layers.30.self_attn.q_proj.weight torch.Size([4096, 4096]) True
273
+ model.layers.30.self_attn.k_proj.weight torch.Size([4096, 4096]) True
274
+ model.layers.30.self_attn.v_proj.weight torch.Size([4096, 4096]) True
275
+ model.layers.30.self_attn.o_proj.weight torch.Size([4096, 4096]) True
276
+ model.layers.30.mlp.gate_proj.weight torch.Size([11008, 4096]) True
277
+ model.layers.30.mlp.up_proj.weight torch.Size([11008, 4096]) True
278
+ model.layers.30.mlp.down_proj.weight torch.Size([4096, 11008]) True
279
+ model.layers.30.input_layernorm.weight torch.Size([4096]) True
280
+ model.layers.30.post_attention_layernorm.weight torch.Size([4096]) True
281
+ model.layers.31.self_attn.q_proj.weight torch.Size([4096, 4096]) True
282
+ model.layers.31.self_attn.k_proj.weight torch.Size([4096, 4096]) True
283
+ model.layers.31.self_attn.v_proj.weight torch.Size([4096, 4096]) True
284
+ model.layers.31.self_attn.o_proj.weight torch.Size([4096, 4096]) True
285
+ model.layers.31.mlp.gate_proj.weight torch.Size([11008, 4096]) True
286
+ model.layers.31.mlp.up_proj.weight torch.Size([11008, 4096]) True
287
+ model.layers.31.mlp.down_proj.weight torch.Size([4096, 11008]) True
288
+ model.layers.31.input_layernorm.weight torch.Size([4096]) True
289
+ model.layers.31.post_attention_layernorm.weight torch.Size([4096]) True
290
+ model.norm.weight torch.Size([4096]) True
291
+ model.molecule_2d_lmm_projector.mlp.0.weight torch.Size([4096, 300]) True
292
+ model.molecule_2d_lmm_projector.mlp.0.bias torch.Size([4096]) True
293
+ model.molecule_2d_lmm_projector.mlp.2.weight torch.Size([4096, 4096]) True
294
+ model.molecule_2d_lmm_projector.mlp.2.bias torch.Size([4096]) True
295
+ lm_head.weight torch.Size([32000, 4096]) True
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<unk>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "<unk>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
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": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "cls_token": "<unk>",
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "mask_token": "<unk>",
37
+ "model_max_length": 2048,
38
+ "pad_token": "<unk>",
39
+ "padding_side": "right",
40
+ "sep_token": "<unk>",
41
+ "sp_model_kwargs": {},
42
+ "spaces_between_special_tokens": false,
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": false
46
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:334c5dacbc1f5a380fe2893fbe82a571a7ddc5af320b070a14acdd3a1daf41a2
3
+ size 6520