Commit
·
50751bc
1
Parent(s):
16bb28e
load model
Browse files- README.md +185 -0
- added_tokens.json +5 -0
- all_results.json +15 -0
- config.json +27 -0
- eval_results.json +10 -0
- generation_config.json +6 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +298 -0
- special_tokens_map.json +10 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: llama7b_rulm_spm_unigram_10_mean_init_tie_12_10_23
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: llama7b_rulm_spm_unigram_10_mean_init_tie_rulm_small_1e_12_10_23
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# llama7b_rulm_spm_unigram_10_mean_init_tie_rulm_small_1e_12_10_23
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [llama7b_rulm_spm_unigram_10_mean_init_tie_12_10_23](https://huggingface.co/llama7b_rulm_spm_unigram_10_mean_init_tie_12_10_23) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.9526
|
| 20 |
+
- Accuracy: 0.4388
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0003
|
| 40 |
+
- train_batch_size: 12
|
| 41 |
+
- eval_batch_size: 12
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 10
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 240
|
| 47 |
+
- total_eval_batch_size: 120
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- lr_scheduler_warmup_steps: 200
|
| 51 |
+
- num_epochs: 1.0
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 56 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|
|
| 57 |
+
| 3.5018 | 0.01 | 1000 | 3.5095 | 0.3768 |
|
| 58 |
+
| 3.3375 | 0.02 | 2000 | 3.3603 | 0.3918 |
|
| 59 |
+
| 3.2694 | 0.02 | 3000 | 3.2995 | 0.3982 |
|
| 60 |
+
| 3.236 | 0.03 | 4000 | 3.2626 | 0.4022 |
|
| 61 |
+
| 3.2131 | 0.04 | 5000 | 3.2350 | 0.4048 |
|
| 62 |
+
| 3.1934 | 0.05 | 6000 | 3.2147 | 0.4073 |
|
| 63 |
+
| 3.177 | 0.06 | 7000 | 3.2006 | 0.4089 |
|
| 64 |
+
| 3.1653 | 0.07 | 8000 | 3.1890 | 0.4097 |
|
| 65 |
+
| 3.1548 | 0.07 | 9000 | 3.1779 | 0.4109 |
|
| 66 |
+
| 3.152 | 0.08 | 10000 | 3.1699 | 0.4119 |
|
| 67 |
+
| 3.1416 | 0.09 | 11000 | 3.1622 | 0.4130 |
|
| 68 |
+
| 3.1387 | 0.1 | 12000 | 3.1561 | 0.4139 |
|
| 69 |
+
| 3.1192 | 0.11 | 13000 | 3.1495 | 0.4143 |
|
| 70 |
+
| 3.1221 | 0.12 | 14000 | 3.1431 | 0.4150 |
|
| 71 |
+
| 3.1136 | 0.12 | 15000 | 3.1391 | 0.4155 |
|
| 72 |
+
| 3.106 | 0.13 | 16000 | 3.1348 | 0.4160 |
|
| 73 |
+
| 3.1023 | 0.14 | 17000 | 3.1312 | 0.4165 |
|
| 74 |
+
| 3.1062 | 0.15 | 18000 | 3.1265 | 0.4172 |
|
| 75 |
+
| 3.1007 | 0.16 | 19000 | 3.1230 | 0.4177 |
|
| 76 |
+
| 3.0979 | 0.16 | 20000 | 3.1201 | 0.4178 |
|
| 77 |
+
| 3.0897 | 0.17 | 21000 | 3.1168 | 0.4179 |
|
| 78 |
+
| 3.0863 | 0.18 | 22000 | 3.1128 | 0.4189 |
|
| 79 |
+
| 3.0898 | 0.19 | 23000 | 3.1097 | 0.4191 |
|
| 80 |
+
| 3.0825 | 0.2 | 24000 | 3.1074 | 0.4191 |
|
| 81 |
+
| 3.0808 | 0.21 | 25000 | 3.1037 | 0.4200 |
|
| 82 |
+
| 3.0774 | 0.21 | 26000 | 3.1032 | 0.4197 |
|
| 83 |
+
| 3.0652 | 0.22 | 27000 | 3.0980 | 0.4202 |
|
| 84 |
+
| 3.0693 | 0.23 | 28000 | 3.0968 | 0.4207 |
|
| 85 |
+
| 3.0665 | 0.24 | 29000 | 3.0944 | 0.4209 |
|
| 86 |
+
| 3.0657 | 0.25 | 30000 | 3.0920 | 0.4210 |
|
| 87 |
+
| 3.0608 | 0.26 | 31000 | 3.0911 | 0.4213 |
|
| 88 |
+
| 3.0647 | 0.26 | 32000 | 3.0896 | 0.4213 |
|
| 89 |
+
| 3.0604 | 0.27 | 33000 | 3.0861 | 0.4217 |
|
| 90 |
+
| 3.0577 | 0.28 | 34000 | 3.0845 | 0.4221 |
|
| 91 |
+
| 3.0606 | 0.29 | 35000 | 3.0814 | 0.4220 |
|
| 92 |
+
| 3.0515 | 0.3 | 36000 | 3.0801 | 0.4227 |
|
| 93 |
+
| 3.0527 | 0.31 | 37000 | 3.0772 | 0.4225 |
|
| 94 |
+
| 3.0507 | 0.31 | 38000 | 3.0758 | 0.4228 |
|
| 95 |
+
| 3.0433 | 0.32 | 39000 | 3.0739 | 0.4234 |
|
| 96 |
+
| 3.0546 | 0.33 | 40000 | 3.0717 | 0.4234 |
|
| 97 |
+
| 3.0484 | 0.34 | 41000 | 3.0697 | 0.4236 |
|
| 98 |
+
| 3.0441 | 0.35 | 42000 | 3.0694 | 0.4236 |
|
| 99 |
+
| 3.0292 | 0.35 | 43000 | 3.0662 | 0.4242 |
|
| 100 |
+
| 3.0384 | 0.36 | 44000 | 3.0643 | 0.4244 |
|
| 101 |
+
| 3.0367 | 0.37 | 45000 | 3.0629 | 0.4240 |
|
| 102 |
+
| 3.0337 | 0.38 | 46000 | 3.0622 | 0.4246 |
|
| 103 |
+
| 3.0385 | 0.39 | 47000 | 3.0599 | 0.4245 |
|
| 104 |
+
| 3.0319 | 0.4 | 48000 | 3.0574 | 0.4250 |
|
| 105 |
+
| 3.0255 | 0.4 | 49000 | 3.0573 | 0.4249 |
|
| 106 |
+
| 3.021 | 0.41 | 50000 | 3.0557 | 0.4253 |
|
| 107 |
+
| 3.0305 | 0.42 | 51000 | 3.0530 | 0.4254 |
|
| 108 |
+
| 3.0248 | 0.43 | 52000 | 3.0528 | 0.4257 |
|
| 109 |
+
| 3.0269 | 0.44 | 53000 | 3.0495 | 0.4261 |
|
| 110 |
+
| 3.0136 | 0.45 | 54000 | 3.0488 | 0.4259 |
|
| 111 |
+
| 3.0156 | 0.45 | 55000 | 3.0468 | 0.4262 |
|
| 112 |
+
| 3.022 | 0.46 | 56000 | 3.0454 | 0.4268 |
|
| 113 |
+
| 3.0193 | 0.47 | 57000 | 3.0442 | 0.4269 |
|
| 114 |
+
| 3.0222 | 0.48 | 58000 | 3.0417 | 0.4270 |
|
| 115 |
+
| 3.0111 | 0.49 | 59000 | 3.0393 | 0.4276 |
|
| 116 |
+
| 3.0148 | 0.49 | 60000 | 3.0384 | 0.4273 |
|
| 117 |
+
| 3.0077 | 0.5 | 61000 | 3.0364 | 0.4276 |
|
| 118 |
+
| 3.0167 | 0.51 | 62000 | 3.0358 | 0.4276 |
|
| 119 |
+
| 3.0049 | 0.52 | 63000 | 3.0343 | 0.4280 |
|
| 120 |
+
| 3.016 | 0.53 | 64000 | 3.0322 | 0.4281 |
|
| 121 |
+
| 3.0103 | 0.54 | 65000 | 3.0297 | 0.4285 |
|
| 122 |
+
| 3.0066 | 0.54 | 66000 | 3.0290 | 0.4284 |
|
| 123 |
+
| 2.9958 | 0.55 | 67000 | 3.0281 | 0.4285 |
|
| 124 |
+
| 3.0062 | 0.56 | 68000 | 3.0266 | 0.4288 |
|
| 125 |
+
| 2.9985 | 0.57 | 69000 | 3.0245 | 0.4289 |
|
| 126 |
+
| 3.0031 | 0.58 | 70000 | 3.0224 | 0.4292 |
|
| 127 |
+
| 2.9894 | 0.59 | 71000 | 3.0214 | 0.4295 |
|
| 128 |
+
| 2.9929 | 0.59 | 72000 | 3.0193 | 0.4296 |
|
| 129 |
+
| 2.9904 | 0.6 | 73000 | 3.0176 | 0.4296 |
|
| 130 |
+
| 2.9989 | 0.61 | 74000 | 3.0171 | 0.4301 |
|
| 131 |
+
| 2.9959 | 0.62 | 75000 | 3.0153 | 0.4301 |
|
| 132 |
+
| 2.9847 | 0.63 | 76000 | 3.0142 | 0.4306 |
|
| 133 |
+
| 2.9892 | 0.63 | 77000 | 3.0127 | 0.4308 |
|
| 134 |
+
| 2.9924 | 0.64 | 78000 | 3.0110 | 0.4310 |
|
| 135 |
+
| 2.991 | 0.65 | 79000 | 3.0096 | 0.4312 |
|
| 136 |
+
| 2.9824 | 0.66 | 80000 | 3.0080 | 0.4311 |
|
| 137 |
+
| 2.9879 | 0.67 | 81000 | 3.0060 | 0.4315 |
|
| 138 |
+
| 2.9764 | 0.68 | 82000 | 3.0042 | 0.4321 |
|
| 139 |
+
| 2.9827 | 0.68 | 83000 | 3.0030 | 0.4315 |
|
| 140 |
+
| 2.9769 | 0.69 | 84000 | 3.0012 | 0.4324 |
|
| 141 |
+
| 2.9788 | 0.7 | 85000 | 3.0002 | 0.4322 |
|
| 142 |
+
| 2.9734 | 0.71 | 86000 | 2.9987 | 0.4325 |
|
| 143 |
+
| 2.9769 | 0.72 | 87000 | 2.9975 | 0.4328 |
|
| 144 |
+
| 2.9676 | 0.73 | 88000 | 2.9959 | 0.4326 |
|
| 145 |
+
| 2.9677 | 0.73 | 89000 | 2.9943 | 0.4330 |
|
| 146 |
+
| 2.9739 | 0.74 | 90000 | 2.9933 | 0.4330 |
|
| 147 |
+
| 2.9691 | 0.75 | 91000 | 2.9914 | 0.4334 |
|
| 148 |
+
| 2.969 | 0.76 | 92000 | 2.9901 | 0.4336 |
|
| 149 |
+
| 2.9602 | 0.77 | 93000 | 2.9889 | 0.4337 |
|
| 150 |
+
| 2.965 | 0.78 | 94000 | 2.9872 | 0.4339 |
|
| 151 |
+
| 2.9627 | 0.78 | 95000 | 2.9853 | 0.4341 |
|
| 152 |
+
| 2.9542 | 0.79 | 96000 | 2.9844 | 0.4340 |
|
| 153 |
+
| 2.9552 | 0.8 | 97000 | 2.9822 | 0.4344 |
|
| 154 |
+
| 2.9576 | 0.81 | 98000 | 2.9812 | 0.4347 |
|
| 155 |
+
| 2.9579 | 0.82 | 99000 | 2.9802 | 0.4348 |
|
| 156 |
+
| 2.9508 | 0.82 | 100000 | 2.9784 | 0.4349 |
|
| 157 |
+
| 2.9551 | 0.83 | 101000 | 2.9771 | 0.4353 |
|
| 158 |
+
| 2.9535 | 0.84 | 102000 | 2.9759 | 0.4357 |
|
| 159 |
+
| 2.9479 | 0.85 | 103000 | 2.9743 | 0.4357 |
|
| 160 |
+
| 2.9542 | 0.86 | 104000 | 2.9732 | 0.4359 |
|
| 161 |
+
| 2.9481 | 0.87 | 105000 | 2.9715 | 0.4360 |
|
| 162 |
+
| 2.941 | 0.87 | 106000 | 2.9697 | 0.4362 |
|
| 163 |
+
| 2.9435 | 0.88 | 107000 | 2.9684 | 0.4365 |
|
| 164 |
+
| 2.9403 | 0.89 | 108000 | 2.9674 | 0.4368 |
|
| 165 |
+
| 2.9453 | 0.9 | 109000 | 2.9661 | 0.4367 |
|
| 166 |
+
| 2.9396 | 0.91 | 110000 | 2.9644 | 0.4372 |
|
| 167 |
+
| 2.9375 | 0.92 | 111000 | 2.9633 | 0.4372 |
|
| 168 |
+
| 2.9284 | 0.92 | 112000 | 2.9621 | 0.4374 |
|
| 169 |
+
| 2.9418 | 0.93 | 113000 | 2.9606 | 0.4376 |
|
| 170 |
+
| 2.934 | 0.94 | 114000 | 2.9594 | 0.4377 |
|
| 171 |
+
| 2.9374 | 0.95 | 115000 | 2.9583 | 0.4380 |
|
| 172 |
+
| 2.9302 | 0.96 | 116000 | 2.9569 | 0.4382 |
|
| 173 |
+
| 2.9273 | 0.96 | 117000 | 2.9560 | 0.4382 |
|
| 174 |
+
| 2.9338 | 0.97 | 118000 | 2.9548 | 0.4384 |
|
| 175 |
+
| 2.9304 | 0.98 | 119000 | 2.9539 | 0.4385 |
|
| 176 |
+
| 2.9361 | 0.99 | 120000 | 2.9531 | 0.4385 |
|
| 177 |
+
| 2.927 | 1.0 | 121000 | 2.9526 | 0.4387 |
|
| 178 |
+
|
| 179 |
+
|
| 180 |
+
### Framework versions
|
| 181 |
+
|
| 182 |
+
- Transformers 4.34.0
|
| 183 |
+
- Pytorch 2.0.1+cu118
|
| 184 |
+
- Datasets 2.14.5
|
| 185 |
+
- Tokenizers 0.14.1
|
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 2,
|
| 3 |
+
"<s>": 1,
|
| 4 |
+
"<unk>": 0
|
| 5 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.43877305016619533,
|
| 4 |
+
"eval_loss": 2.9525771141052246,
|
| 5 |
+
"eval_runtime": 36.6024,
|
| 6 |
+
"eval_samples": 11366,
|
| 7 |
+
"eval_samples_per_second": 310.526,
|
| 8 |
+
"eval_steps_per_second": 2.595,
|
| 9 |
+
"perplexity": 19.155255451875632,
|
| 10 |
+
"train_loss": 3.0377933233989878,
|
| 11 |
+
"train_runtime": 170019.0203,
|
| 12 |
+
"train_samples": 29107055,
|
| 13 |
+
"train_samples_per_second": 171.199,
|
| 14 |
+
"train_steps_per_second": 0.713
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "llama7b_rulm_spm_unigram_10_mean_init_tie_12_10_23",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_hidden_layers": 32,
|
| 17 |
+
"num_key_value_heads": 32,
|
| 18 |
+
"pretraining_tp": 1,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 10000.0,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float16",
|
| 24 |
+
"transformers_version": "4.34.0",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 32000
|
| 27 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.43877305016619533,
|
| 4 |
+
"eval_loss": 2.9525771141052246,
|
| 5 |
+
"eval_runtime": 36.6024,
|
| 6 |
+
"eval_samples": 11366,
|
| 7 |
+
"eval_samples_per_second": 310.526,
|
| 8 |
+
"eval_steps_per_second": 2.595,
|
| 9 |
+
"perplexity": 19.155255451875632
|
| 10 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.34.0"
|
| 6 |
+
}
|
pytorch_model-00001-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2b9a97831ef3db6e8d5c5f9b93ccfdf794a33c8e15f4a7ab9e0d4bae9bf5ec7
|
| 3 |
+
size 9976620122
|
pytorch_model-00002-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7564621ff0bd28eee118bd5b963e8655b550b817a9b09e07cd6727deb83b5b09
|
| 3 |
+
size 3500310787
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13476831232
|
| 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.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 296 |
+
"model.norm.weight": "pytorch_model-00002-of-00002.bin"
|
| 297 |
+
}
|
| 298 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": "<s>",
|
| 8 |
+
"eos_token": "</s>",
|
| 9 |
+
"unk_token": "<unk>"
|
| 10 |
+
}
|
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 sha256:22ae0ac060bfed5f12c495732c9954f6f8c3485a745eca5d9092c5c07dcae0d1
|
| 3 |
+
size 1014831
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [
|
| 29 |
+
"<unk>",
|
| 30 |
+
"<s>",
|
| 31 |
+
"</s>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": "<s>",
|
| 34 |
+
"clean_up_tokenization_spaces": false,
|
| 35 |
+
"eos_token": "</s>",
|
| 36 |
+
"legacy": true,
|
| 37 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
+
"pad_token": null,
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": true
|
| 44 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 3.0377933233989878,
|
| 4 |
+
"train_runtime": 170019.0203,
|
| 5 |
+
"train_samples": 29107055,
|
| 6 |
+
"train_samples_per_second": 171.199,
|
| 7 |
+
"train_steps_per_second": 0.713
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:330ea01742e8019b12ed3789e4ede3551b58f67d2f1b9650b153ee0977f593c2
|
| 3 |
+
size 5627
|