Hugging Face's logo

loganamcnichols
/
3neg4_2epoch_llama

Text Generation
Transformers
PyTorch
TensorBoard
llama
Trained with AutoTrain
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
loganamcnichols commited on
Commit
6f75aa9
·
1 Parent(s): 8dbcf3f

Upload folder using huggingface_hub

Browse files
Files changed (41) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-60/README.md +20 -0
  5. checkpoint-60/adapter_config.json +21 -0
  6. checkpoint-60/adapter_model.bin +3 -0
  7. checkpoint-60/optimizer.pt +3 -0
  8. checkpoint-60/rng_state.pth +3 -0
  9. checkpoint-60/scheduler.pt +3 -0
  10. checkpoint-60/trainer_state.json +400 -0
  11. checkpoint-60/training_args.bin +3 -0
  12. config.json +26 -0
  13. generation_config.json +10 -0
  14. pytorch_model-00001-of-00002.bin +3 -0
  15. pytorch_model-00002-of-00002.bin +3 -0
  16. pytorch_model.bin.index.json +330 -0
  17. runs/Aug16_17-41-19_242bd1be4431/events.out.tfevents.1692207679.242bd1be4431.4679.0 +3 -0
  18. runs/Aug16_17-59-41_242bd1be4431/events.out.tfevents.1692208782.242bd1be4431.9620.0 +3 -0
  19. runs/Aug16_18-18-25_242bd1be4431/events.out.tfevents.1692209905.242bd1be4431.14298.0 +3 -0
  20. runs/Aug16_18-37-40_242bd1be4431/events.out.tfevents.1692211060.242bd1be4431.19066.0 +3 -0
  21. runs/Aug16_18-56-06_242bd1be4431/events.out.tfevents.1692212167.242bd1be4431.23640.0 +3 -0
  22. runs/Aug16_19-14-15_242bd1be4431/events.out.tfevents.1692213256.242bd1be4431.28158.0 +3 -0
  23. runs/Aug16_19-32-22_242bd1be4431/events.out.tfevents.1692214343.242bd1be4431.32652.0 +3 -0
  24. runs/Aug16_19-44-58_242bd1be4431/events.out.tfevents.1692215099.242bd1be4431.35903.0 +3 -0
  25. runs/Aug16_20-03-53_242bd1be4431/events.out.tfevents.1692216234.242bd1be4431.40570.0 +3 -0
  26. runs/Aug16_20-42-48_242bd1be4431/events.out.tfevents.1692218568.242bd1be4431.48855.0 +3 -0
  27. runs/Aug16_21-03-39_242bd1be4431/events.out.tfevents.1692219819.242bd1be4431.55310.0 +3 -0
  28. runs/Aug16_21-22-22_242bd1be4431/events.out.tfevents.1692220942.242bd1be4431.59970.0 +3 -0
  29. runs/Aug16_21-47-01_242bd1be4431/events.out.tfevents.1692222421.242bd1be4431.66024.0 +3 -0
  30. runs/Aug16_22-06-54_242bd1be4431/events.out.tfevents.1692223614.242bd1be4431.70906.0 +3 -0
  31. runs/Aug16_22-26-11_242bd1be4431/events.out.tfevents.1692224772.242bd1be4431.75636.0 +3 -0
  32. runs/Aug16_22-45-30_242bd1be4431/events.out.tfevents.1692225930.242bd1be4431.80402.0 +3 -0
  33. runs/Aug16_23-03-49_242bd1be4431/events.out.tfevents.1692227029.242bd1be4431.84880.0 +3 -0
  34. runs/Aug16_23-22-49_242bd1be4431/events.out.tfevents.1692228169.242bd1be4431.89552.0 +3 -0
  35. runs/Aug16_23-40-18_242bd1be4431/events.out.tfevents.1692229219.242bd1be4431.93864.0 +3 -0
  36. runs/Aug17_00-00-53_242bd1be4431/events.out.tfevents.1692230453.242bd1be4431.98936.0 +3 -0
  37. special_tokens_map.json +23 -0
  38. tokenizer.json +0 -0
  39. tokenizer.model +3 -0
  40. tokenizer_config.json +33 -0
  41. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation
5
+ widget:
6
+ - text: "I love AutoTrain because "
7
+ ---
8
+
9
+ # Model Trained Using AutoTrain
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "SEQ_CLS"
21
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d6cea2ad0f98d6ae0ee0af05590f91433185b29f5e164900e9bebb0a646e36
3
+ size 33617169
checkpoint-60/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.4.0
checkpoint-60/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "SEQ_CLS"
21
+ }
checkpoint-60/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d6cea2ad0f98d6ae0ee0af05590f91433185b29f5e164900e9bebb0a646e36
3
+ size 33617169
checkpoint-60/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f7c8082eb4f27dce41a6558d033c3ca2f4ef3a111cc8dfde6613b7cdf498361
3
+ size 67250117
checkpoint-60/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e79a45fe4229e63671256134ad7bf48673273a642f8b78620a0a98184e769fdf
3
+ size 14575
checkpoint-60/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e1aca1d6723a743f570c53af1b7b8b3f5f61faa837662f7d601a0cc2bb664e
3
+ size 627
checkpoint-60/trainer_state.json ADDED
@@ -0,0 +1,400 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.6558432579040527,
3
+ "best_model_checkpoint": "fb-model-test-1/checkpoint-60",
4
+ "epoch": 2.0,
5
+ "global_step": 60,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.03,
12
+ "learning_rate": 4.9999999999999996e-05,
13
+ "loss": 114.7306,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.07,
18
+ "learning_rate": 9.999999999999999e-05,
19
+ "loss": 147.1084,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.1,
24
+ "learning_rate": 0.00015,
25
+ "loss": 138.5689,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.13,
30
+ "learning_rate": 0.00019999999999999998,
31
+ "loss": 148.6435,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.17,
36
+ "learning_rate": 0.00025,
37
+ "loss": 136.1586,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.2,
42
+ "learning_rate": 0.0003,
43
+ "loss": 127.0481,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.23,
48
+ "learning_rate": 0.00029444444444444445,
49
+ "loss": 117.9231,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.27,
54
+ "learning_rate": 0.0002888888888888888,
55
+ "loss": 69.7386,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.3,
60
+ "learning_rate": 0.0002833333333333333,
61
+ "loss": 71.1253,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.33,
66
+ "learning_rate": 0.0002777777777777778,
67
+ "loss": 25.4039,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.37,
72
+ "learning_rate": 0.0002722222222222222,
73
+ "loss": 31.6795,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.4,
78
+ "learning_rate": 0.0002666666666666666,
79
+ "loss": 16.2109,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.43,
84
+ "learning_rate": 0.0002611111111111111,
85
+ "loss": 17.0603,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.47,
90
+ "learning_rate": 0.00025555555555555553,
91
+ "loss": 14.7974,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.5,
96
+ "learning_rate": 0.00025,
97
+ "loss": 19.4913,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.53,
102
+ "learning_rate": 0.00024444444444444443,
103
+ "loss": 14.2243,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.57,
108
+ "learning_rate": 0.00023888888888888885,
109
+ "loss": 17.5441,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.6,
114
+ "learning_rate": 0.0002333333333333333,
115
+ "loss": 9.5677,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.63,
120
+ "learning_rate": 0.00022777777777777778,
121
+ "loss": 5.9725,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.67,
126
+ "learning_rate": 0.00022222222222222218,
127
+ "loss": 8.3619,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.7,
132
+ "learning_rate": 0.00021666666666666666,
133
+ "loss": 20.6023,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.73,
138
+ "learning_rate": 0.0002111111111111111,
139
+ "loss": 14.2163,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.77,
144
+ "learning_rate": 0.00020555555555555556,
145
+ "loss": 5.6454,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.8,
150
+ "learning_rate": 0.00019999999999999998,
151
+ "loss": 9.0549,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.83,
156
+ "learning_rate": 0.00019444444444444443,
157
+ "loss": 4.6107,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.87,
162
+ "learning_rate": 0.00018888888888888888,
163
+ "loss": 7.6686,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.9,
168
+ "learning_rate": 0.00018333333333333334,
169
+ "loss": 3.9631,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.93,
174
+ "learning_rate": 0.00017777777777777776,
175
+ "loss": 1.7585,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.97,
180
+ "learning_rate": 0.0001722222222222222,
181
+ "loss": 3.051,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 1.0,
186
+ "learning_rate": 0.00016666666666666666,
187
+ "loss": 1.2488,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 1.0,
192
+ "eval_Explained Variance": -0.5409103631973267,
193
+ "eval_MAE": 2.6195828914642334,
194
+ "eval_MSE": 9.606053352355957,
195
+ "eval_R2": -2.9621435379349452,
196
+ "eval_loss": 9.606053352355957,
197
+ "eval_runtime": 7.3307,
198
+ "eval_samples_per_second": 6.548,
199
+ "eval_steps_per_second": 1.637,
200
+ "step": 30
201
+ },
202
+ {
203
+ "epoch": 1.03,
204
+ "learning_rate": 0.0001611111111111111,
205
+ "loss": 3.9871,
206
+ "step": 31
207
+ },
208
+ {
209
+ "epoch": 1.07,
210
+ "learning_rate": 0.00015555555555555554,
211
+ "loss": 10.1596,
212
+ "step": 32
213
+ },
214
+ {
215
+ "epoch": 1.1,
216
+ "learning_rate": 0.00015,
217
+ "loss": 4.9952,
218
+ "step": 33
219
+ },
220
+ {
221
+ "epoch": 1.13,
222
+ "learning_rate": 0.0001444444444444444,
223
+ "loss": 3.4312,
224
+ "step": 34
225
+ },
226
+ {
227
+ "epoch": 1.17,
228
+ "learning_rate": 0.0001388888888888889,
229
+ "loss": 6.7105,
230
+ "step": 35
231
+ },
232
+ {
233
+ "epoch": 1.2,
234
+ "learning_rate": 0.0001333333333333333,
235
+ "loss": 3.0607,
236
+ "step": 36
237
+ },
238
+ {
239
+ "epoch": 1.23,
240
+ "learning_rate": 0.00012777777777777776,
241
+ "loss": 2.3403,
242
+ "step": 37
243
+ },
244
+ {
245
+ "epoch": 1.27,
246
+ "learning_rate": 0.00012222222222222221,
247
+ "loss": 2.2802,
248
+ "step": 38
249
+ },
250
+ {
251
+ "epoch": 1.3,
252
+ "learning_rate": 0.00011666666666666665,
253
+ "loss": 1.1622,
254
+ "step": 39
255
+ },
256
+ {
257
+ "epoch": 1.33,
258
+ "learning_rate": 0.00011111111111111109,
259
+ "loss": 1.9408,
260
+ "step": 40
261
+ },
262
+ {
263
+ "epoch": 1.37,
264
+ "learning_rate": 0.00010555555555555555,
265
+ "loss": 5.6253,
266
+ "step": 41
267
+ },
268
+ {
269
+ "epoch": 1.4,
270
+ "learning_rate": 9.999999999999999e-05,
271
+ "loss": 1.2139,
272
+ "step": 42
273
+ },
274
+ {
275
+ "epoch": 1.43,
276
+ "learning_rate": 9.444444444444444e-05,
277
+ "loss": 2.7765,
278
+ "step": 43
279
+ },
280
+ {
281
+ "epoch": 1.47,
282
+ "learning_rate": 8.888888888888888e-05,
283
+ "loss": 2.3549,
284
+ "step": 44
285
+ },
286
+ {
287
+ "epoch": 1.5,
288
+ "learning_rate": 8.333333333333333e-05,
289
+ "loss": 1.6461,
290
+ "step": 45
291
+ },
292
+ {
293
+ "epoch": 1.53,
294
+ "learning_rate": 7.777777777777777e-05,
295
+ "loss": 6.1876,
296
+ "step": 46
297
+ },
298
+ {
299
+ "epoch": 1.57,
300
+ "learning_rate": 7.22222222222222e-05,
301
+ "loss": 12.1191,
302
+ "step": 47
303
+ },
304
+ {
305
+ "epoch": 1.6,
306
+ "learning_rate": 6.666666666666666e-05,
307
+ "loss": 2.2652,
308
+ "step": 48
309
+ },
310
+ {
311
+ "epoch": 1.63,
312
+ "learning_rate": 6.111111111111111e-05,
313
+ "loss": 0.9004,
314
+ "step": 49
315
+ },
316
+ {
317
+ "epoch": 1.67,
318
+ "learning_rate": 5.5555555555555545e-05,
319
+ "loss": 1.2818,
320
+ "step": 50
321
+ },
322
+ {
323
+ "epoch": 1.7,
324
+ "learning_rate": 4.9999999999999996e-05,
325
+ "loss": 0.7738,
326
+ "step": 51
327
+ },
328
+ {
329
+ "epoch": 1.73,
330
+ "learning_rate": 4.444444444444444e-05,
331
+ "loss": 3.9364,
332
+ "step": 52
333
+ },
334
+ {
335
+ "epoch": 1.77,
336
+ "learning_rate": 3.8888888888888884e-05,
337
+ "loss": 2.4493,
338
+ "step": 53
339
+ },
340
+ {
341
+ "epoch": 1.8,
342
+ "learning_rate": 3.333333333333333e-05,
343
+ "loss": 1.4627,
344
+ "step": 54
345
+ },
346
+ {
347
+ "epoch": 1.83,
348
+ "learning_rate": 2.7777777777777772e-05,
349
+ "loss": 2.1286,
350
+ "step": 55
351
+ },
352
+ {
353
+ "epoch": 1.87,
354
+ "learning_rate": 2.222222222222222e-05,
355
+ "loss": 1.6587,
356
+ "step": 56
357
+ },
358
+ {
359
+ "epoch": 1.9,
360
+ "learning_rate": 1.6666666666666664e-05,
361
+ "loss": 0.4811,
362
+ "step": 57
363
+ },
364
+ {
365
+ "epoch": 1.93,
366
+ "learning_rate": 1.111111111111111e-05,
367
+ "loss": 2.2352,
368
+ "step": 58
369
+ },
370
+ {
371
+ "epoch": 1.97,
372
+ "learning_rate": 5.555555555555555e-06,
373
+ "loss": 1.6483,
374
+ "step": 59
375
+ },
376
+ {
377
+ "epoch": 2.0,
378
+ "learning_rate": 0.0,
379
+ "loss": 2.2316,
380
+ "step": 60
381
+ },
382
+ {
383
+ "epoch": 2.0,
384
+ "eval_Explained Variance": -0.0942157506942749,
385
+ "eval_MAE": 1.253036379814148,
386
+ "eval_MSE": 2.6558432579040527,
387
+ "eval_R2": -0.09543758153656778,
388
+ "eval_loss": 2.6558432579040527,
389
+ "eval_runtime": 7.2899,
390
+ "eval_samples_per_second": 6.584,
391
+ "eval_steps_per_second": 1.646,
392
+ "step": 60
393
+ }
394
+ ],
395
+ "max_steps": 60,
396
+ "num_train_epochs": 2,
397
+ "total_flos": 1166929582620672.0,
398
+ "trial_name": null,
399
+ "trial_params": null
400
+ }
checkpoint-60/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb2abc46c8b2506079e905db5b0c05a05767f4d9c84857507fe707381b8787d
3
+ size 3963
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.31.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.31.0"
10
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af44c9f76ae8ded0521be4f10d8f7fa4e34f9c05e0b55141a86cef2b26ad339b
3
+ size 9976634558
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb8356d607739906cbf4a52a6b2ecc6505b73d83ddbc223a132b832acbe388e
3
+ size 3500315539
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13476839424
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
328
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
329
+ }
330
+ }
runs/Aug16_17-41-19_242bd1be4431/events.out.tfevents.1692207679.242bd1be4431.4679.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:782c6e3298f0b8def5f49c85ffa4fb504f6d9b849c37a758938e78fae73321cc
3
+ size 45855
runs/Aug16_17-59-41_242bd1be4431/events.out.tfevents.1692208782.242bd1be4431.9620.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac820fc23f59515e676362fa90d569787ce9ec31626b005908abbb3797b9c6b3
3
+ size 45854
runs/Aug16_18-18-25_242bd1be4431/events.out.tfevents.1692209905.242bd1be4431.14298.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e37ba2117af96d6497804eeaa3f7648d8e11ecde1bfd9b8c0b6c0c1fce7226a
3
+ size 45855
runs/Aug16_18-37-40_242bd1be4431/events.out.tfevents.1692211060.242bd1be4431.19066.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:893656e2db6fcbe06c6466c3d4d454d2e8965765699e4046858fb11471835bed
3
+ size 45854
runs/Aug16_18-56-06_242bd1be4431/events.out.tfevents.1692212167.242bd1be4431.23640.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3b14db6df287f1e3f62697ded0ed4e1fb3d9513ca905cc4f9bec3ccd9783302
3
+ size 45855
runs/Aug16_19-14-15_242bd1be4431/events.out.tfevents.1692213256.242bd1be4431.28158.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d18f338b11fc87e35cdd4e8e1b46e04c29e352bd5e574c914c3d28e3e59935
3
+ size 45856
runs/Aug16_19-32-22_242bd1be4431/events.out.tfevents.1692214343.242bd1be4431.32652.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:967a3971aff2cc9379b30b2073da7131fd70dce1233f30adbadd1e270635e6d0
3
+ size 36235
runs/Aug16_19-44-58_242bd1be4431/events.out.tfevents.1692215099.242bd1be4431.35903.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f011581dc347c054819709e89a4250f9faa84d646e16e553b4f5539ea305e7c4
3
+ size 45856
runs/Aug16_20-03-53_242bd1be4431/events.out.tfevents.1692216234.242bd1be4431.40570.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb2046f22c7e7ae367a18054dfe9846f45c59c5a2ca1a73642175d91523b59c
3
+ size 45856
runs/Aug16_20-42-48_242bd1be4431/events.out.tfevents.1692218568.242bd1be4431.48855.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfcd22fed95868d58f62611aef3e5312b780c3b283b8d7d04ac9ae161382d471
3
+ size 45858
runs/Aug16_21-03-39_242bd1be4431/events.out.tfevents.1692219819.242bd1be4431.55310.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:664aeda535abe6cfde35f7ed9c64ca9fa27e35ad7148b172b301c1e7903c4bb9
3
+ size 45856
runs/Aug16_21-22-22_242bd1be4431/events.out.tfevents.1692220942.242bd1be4431.59970.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf57066c49619b0d7e74ca71b491e0498c45dff84265e2e2b77bdd589865e436
3
+ size 45856
runs/Aug16_21-47-01_242bd1be4431/events.out.tfevents.1692222421.242bd1be4431.66024.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb98fe63ddea688118e0b41fcce07c6e2576cdc68573eabef0f51c89dade0e73
3
+ size 40672
runs/Aug16_22-06-54_242bd1be4431/events.out.tfevents.1692223614.242bd1be4431.70906.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cdf787a737aad40fad18d094a2a512a4657c5ffe3e88633633eab806fbb6df8
3
+ size 45856
runs/Aug16_22-26-11_242bd1be4431/events.out.tfevents.1692224772.242bd1be4431.75636.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295cb577bbd4b044fae13ba6cc50564d36c2bafa3f181aefd5faf10f41361335
3
+ size 45856
runs/Aug16_22-45-30_242bd1be4431/events.out.tfevents.1692225930.242bd1be4431.80402.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bfcef2519bf889cb2ecb524de53c50c72c9d6fad07e52e47359f4e17d4a4fcc
3
+ size 40673
runs/Aug16_23-03-49_242bd1be4431/events.out.tfevents.1692227029.242bd1be4431.84880.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a6a355457a331524c10184e27d6ad72c20548cb5216908aa9d9050d4aaab9ac
3
+ size 45855
runs/Aug16_23-22-49_242bd1be4431/events.out.tfevents.1692228169.242bd1be4431.89552.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb68486061a2763410fcd4834c8c6d0712762db2c0729294b3b8663457e6288a
3
+ size 40673
runs/Aug16_23-40-18_242bd1be4431/events.out.tfevents.1692229219.242bd1be4431.93864.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e50ab886c7a233d5d2de7bc2d04e11119ccba8d47e2238cb5541148f9054225c
3
+ size 45856
runs/Aug17_00-00-53_242bd1be4431/events.out.tfevents.1692230453.242bd1be4431.98936.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46043ceac58eeaece554c5cfa44e47fdc63b5ea920ce61882866ba63d5f655d
3
+ size 14971
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb2abc46c8b2506079e905db5b0c05a05767f4d9c84857507fe707381b8787d
3
+ size 3963