Model save
Browse files- README.md +119 -0
- all_results.json +21 -0
- eval_results.json +16 -0
- generation_config.json +7 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +692 -0
- runs/Jan16_11-23-05_main1/events.out.tfevents.1705404271.main1.10305.0 +2 -2
- runs/Jan16_11-23-05_main1/events.out.tfevents.1705481079.main1.10305.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: ondevicellm/tinyllama_moe_sft_ultrachat_epochs3
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- dpo
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: tinyllama_moe_dpo_ultrafeedback_epochs5
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# tinyllama_moe_dpo_ultrafeedback_epochs5
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [ondevicellm/tinyllama_moe_sft_ultrachat_epochs3](https://huggingface.co/ondevicellm/tinyllama_moe_sft_ultrachat_epochs3) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5698
|
| 21 |
+
- Rewards/chosen: -1.5249
|
| 22 |
+
- Rewards/rejected: -2.1850
|
| 23 |
+
- Rewards/accuracies: 0.7460
|
| 24 |
+
- Rewards/margins: 0.6601
|
| 25 |
+
- Logps/rejected: -525.1185
|
| 26 |
+
- Logps/chosen: -501.3176
|
| 27 |
+
- Logits/rejected: -1.7144
|
| 28 |
+
- Logits/chosen: -1.8206
|
| 29 |
+
|
| 30 |
+
## Model description
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Intended uses & limitations
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training and evaluation data
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Training procedure
|
| 43 |
+
|
| 44 |
+
### Training hyperparameters
|
| 45 |
+
|
| 46 |
+
The following hyperparameters were used during training:
|
| 47 |
+
- learning_rate: 5e-07
|
| 48 |
+
- train_batch_size: 8
|
| 49 |
+
- eval_batch_size: 8
|
| 50 |
+
- seed: 42
|
| 51 |
+
- distributed_type: multi-GPU
|
| 52 |
+
- num_devices: 4
|
| 53 |
+
- gradient_accumulation_steps: 2
|
| 54 |
+
- total_train_batch_size: 64
|
| 55 |
+
- total_eval_batch_size: 32
|
| 56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 57 |
+
- lr_scheduler_type: cosine
|
| 58 |
+
- lr_scheduler_warmup_steps: 96
|
| 59 |
+
- num_epochs: 5
|
| 60 |
+
|
| 61 |
+
### Training results
|
| 62 |
+
|
| 63 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
| 64 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
| 65 |
+
| 0.6916 | 0.1 | 100 | 0.6914 | 0.0044 | -0.0007 | 0.6290 | 0.0050 | -306.6867 | -348.3935 | -2.7893 | -2.8529 |
|
| 66 |
+
| 0.6838 | 0.21 | 200 | 0.6833 | 0.0222 | -0.0020 | 0.6548 | 0.0242 | -306.8183 | -346.6077 | -2.7745 | -2.8394 |
|
| 67 |
+
| 0.6683 | 0.31 | 300 | 0.6720 | 0.0087 | -0.0449 | 0.6647 | 0.0536 | -311.1083 | -347.9552 | -2.7457 | -2.8123 |
|
| 68 |
+
| 0.655 | 0.42 | 400 | 0.6583 | -0.0568 | -0.1516 | 0.6766 | 0.0948 | -321.7766 | -354.5066 | -2.6922 | -2.7610 |
|
| 69 |
+
| 0.6435 | 0.52 | 500 | 0.6453 | -0.1710 | -0.3165 | 0.6706 | 0.1455 | -338.2649 | -365.9251 | -2.6457 | -2.7160 |
|
| 70 |
+
| 0.641 | 0.63 | 600 | 0.6366 | -0.2120 | -0.3985 | 0.6825 | 0.1865 | -346.4684 | -370.0310 | -2.5893 | -2.6615 |
|
| 71 |
+
| 0.6207 | 0.73 | 700 | 0.6319 | -0.2615 | -0.4812 | 0.6706 | 0.2197 | -354.7403 | -374.9797 | -2.5381 | -2.6120 |
|
| 72 |
+
| 0.6025 | 0.84 | 800 | 0.6249 | -0.3306 | -0.5888 | 0.6964 | 0.2583 | -365.5025 | -381.8849 | -2.4644 | -2.5413 |
|
| 73 |
+
| 0.6317 | 0.94 | 900 | 0.6185 | -0.5597 | -0.8426 | 0.7063 | 0.2829 | -390.8784 | -404.7987 | -2.4027 | -2.4814 |
|
| 74 |
+
| 0.6087 | 1.05 | 1000 | 0.6137 | -0.5045 | -0.8126 | 0.7004 | 0.3081 | -387.8767 | -399.2817 | -2.3842 | -2.4637 |
|
| 75 |
+
| 0.5993 | 1.15 | 1100 | 0.6077 | -0.6040 | -0.9415 | 0.7044 | 0.3375 | -400.7663 | -409.2302 | -2.3436 | -2.4254 |
|
| 76 |
+
| 0.5628 | 1.26 | 1200 | 0.6026 | -0.8401 | -1.2238 | 0.7103 | 0.3837 | -429.0004 | -432.8431 | -2.2635 | -2.3475 |
|
| 77 |
+
| 0.5856 | 1.36 | 1300 | 0.5971 | -0.7421 | -1.1421 | 0.7242 | 0.3999 | -420.8279 | -423.0439 | -2.2233 | -2.3091 |
|
| 78 |
+
| 0.5672 | 1.47 | 1400 | 0.5930 | -0.7829 | -1.2202 | 0.7143 | 0.4373 | -428.6362 | -427.1146 | -2.1938 | -2.2804 |
|
| 79 |
+
| 0.5536 | 1.57 | 1500 | 0.5872 | -0.8347 | -1.2945 | 0.7202 | 0.4599 | -436.0717 | -432.2956 | -2.1433 | -2.2324 |
|
| 80 |
+
| 0.5669 | 1.67 | 1600 | 0.5858 | -0.7867 | -1.2636 | 0.7163 | 0.4769 | -432.9818 | -427.4996 | -2.1168 | -2.2065 |
|
| 81 |
+
| 0.5312 | 1.78 | 1700 | 0.5831 | -0.9925 | -1.4919 | 0.7262 | 0.4994 | -455.8103 | -448.0764 | -2.0492 | -2.1424 |
|
| 82 |
+
| 0.5596 | 1.88 | 1800 | 0.5798 | -1.0023 | -1.5297 | 0.7361 | 0.5274 | -459.5894 | -449.0625 | -2.0168 | -2.1124 |
|
| 83 |
+
| 0.5489 | 1.99 | 1900 | 0.5813 | -0.8832 | -1.3904 | 0.7202 | 0.5072 | -445.6621 | -437.1509 | -2.0039 | -2.0990 |
|
| 84 |
+
| 0.5327 | 2.09 | 2000 | 0.5795 | -0.9218 | -1.4418 | 0.7242 | 0.5200 | -450.7982 | -441.0125 | -1.9626 | -2.0594 |
|
| 85 |
+
| 0.5225 | 2.2 | 2100 | 0.5779 | -1.1696 | -1.7317 | 0.7401 | 0.5621 | -479.7868 | -465.7886 | -1.9207 | -2.0189 |
|
| 86 |
+
| 0.5085 | 2.3 | 2200 | 0.5769 | -1.1637 | -1.7425 | 0.7321 | 0.5789 | -480.8718 | -465.1949 | -1.8892 | -1.9891 |
|
| 87 |
+
| 0.5255 | 2.41 | 2300 | 0.5770 | -1.2191 | -1.7925 | 0.7341 | 0.5734 | -485.8650 | -470.7390 | -1.8632 | -1.9614 |
|
| 88 |
+
| 0.5116 | 2.51 | 2400 | 0.5742 | -1.1139 | -1.6936 | 0.7381 | 0.5798 | -475.9834 | -460.2151 | -1.8765 | -1.9749 |
|
| 89 |
+
| 0.5279 | 2.62 | 2500 | 0.5741 | -1.1556 | -1.7455 | 0.7361 | 0.5899 | -481.1734 | -464.3928 | -1.8664 | -1.9651 |
|
| 90 |
+
| 0.4795 | 2.72 | 2600 | 0.5745 | -1.1558 | -1.7459 | 0.7321 | 0.5900 | -481.2056 | -464.4143 | -1.8345 | -1.9355 |
|
| 91 |
+
| 0.5217 | 2.83 | 2700 | 0.5699 | -1.3475 | -1.9659 | 0.7440 | 0.6184 | -503.2092 | -483.5756 | -1.7956 | -1.8981 |
|
| 92 |
+
| 0.4945 | 2.93 | 2800 | 0.5699 | -1.3594 | -1.9727 | 0.7381 | 0.6132 | -503.8864 | -484.7731 | -1.8126 | -1.9141 |
|
| 93 |
+
| 0.477 | 3.04 | 2900 | 0.5721 | -1.3627 | -1.9877 | 0.7361 | 0.6250 | -505.3890 | -485.0972 | -1.7954 | -1.8980 |
|
| 94 |
+
| 0.4754 | 3.14 | 3000 | 0.5729 | -1.4117 | -2.0575 | 0.7321 | 0.6458 | -512.3726 | -490.0027 | -1.7473 | -1.8516 |
|
| 95 |
+
| 0.4696 | 3.24 | 3100 | 0.5708 | -1.5486 | -2.1921 | 0.7282 | 0.6435 | -525.8281 | -503.6902 | -1.7318 | -1.8363 |
|
| 96 |
+
| 0.4804 | 3.35 | 3200 | 0.5730 | -1.5037 | -2.1632 | 0.7321 | 0.6595 | -522.9344 | -499.1950 | -1.7097 | -1.8163 |
|
| 97 |
+
| 0.483 | 3.45 | 3300 | 0.5706 | -1.5793 | -2.2451 | 0.7302 | 0.6658 | -531.1252 | -506.7562 | -1.7082 | -1.8147 |
|
| 98 |
+
| 0.4791 | 3.56 | 3400 | 0.5723 | -1.4505 | -2.1095 | 0.7262 | 0.6590 | -517.5656 | -493.8777 | -1.7222 | -1.8274 |
|
| 99 |
+
| 0.4866 | 3.66 | 3500 | 0.5713 | -1.5091 | -2.1642 | 0.7381 | 0.6551 | -523.0358 | -499.7364 | -1.7191 | -1.8243 |
|
| 100 |
+
| 0.4651 | 3.77 | 3600 | 0.5731 | -1.4577 | -2.1177 | 0.7401 | 0.6600 | -518.3928 | -494.6030 | -1.7161 | -1.8217 |
|
| 101 |
+
| 0.483 | 3.87 | 3700 | 0.5708 | -1.4280 | -2.0759 | 0.7361 | 0.6479 | -514.2116 | -491.6330 | -1.7275 | -1.8325 |
|
| 102 |
+
| 0.4859 | 3.98 | 3800 | 0.5698 | -1.5249 | -2.1850 | 0.7460 | 0.6601 | -525.1185 | -501.3176 | -1.7144 | -1.8206 |
|
| 103 |
+
| 0.476 | 4.08 | 3900 | 0.5701 | -1.5060 | -2.1668 | 0.7440 | 0.6608 | -523.2975 | -499.4326 | -1.7157 | -1.8219 |
|
| 104 |
+
| 0.4553 | 4.19 | 4000 | 0.5705 | -1.5415 | -2.2042 | 0.7361 | 0.6626 | -527.0359 | -502.9834 | -1.7053 | -1.8120 |
|
| 105 |
+
| 0.4864 | 4.29 | 4100 | 0.5721 | -1.5310 | -2.1997 | 0.7381 | 0.6687 | -526.5859 | -501.9312 | -1.6982 | -1.8054 |
|
| 106 |
+
| 0.4402 | 4.4 | 4200 | 0.5720 | -1.5402 | -2.2110 | 0.7401 | 0.6708 | -527.7231 | -502.8538 | -1.6937 | -1.8008 |
|
| 107 |
+
| 0.4619 | 4.5 | 4300 | 0.5712 | -1.5462 | -2.2169 | 0.7361 | 0.6706 | -528.3046 | -503.4531 | -1.6931 | -1.8004 |
|
| 108 |
+
| 0.4421 | 4.6 | 4400 | 0.5710 | -1.5628 | -2.2323 | 0.7381 | 0.6695 | -529.8489 | -505.1078 | -1.6915 | -1.7989 |
|
| 109 |
+
| 0.4518 | 4.71 | 4500 | 0.5711 | -1.5704 | -2.2407 | 0.7361 | 0.6703 | -530.6893 | -505.8743 | -1.6913 | -1.7985 |
|
| 110 |
+
| 0.4508 | 4.81 | 4600 | 0.5715 | -1.5739 | -2.2436 | 0.7381 | 0.6697 | -530.9782 | -506.2146 | -1.6908 | -1.7981 |
|
| 111 |
+
| 0.484 | 4.92 | 4700 | 0.5716 | -1.5737 | -2.2419 | 0.7321 | 0.6682 | -530.8127 | -506.2016 | -1.6901 | -1.7976 |
|
| 112 |
+
|
| 113 |
+
|
| 114 |
+
### Framework versions
|
| 115 |
+
|
| 116 |
+
- Transformers 4.36.2
|
| 117 |
+
- Pytorch 2.1.2+cu118
|
| 118 |
+
- Datasets 2.14.6
|
| 119 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_logits/chosen": -1.8205610513687134,
|
| 4 |
+
"eval_logits/rejected": -1.714389681816101,
|
| 5 |
+
"eval_logps/chosen": -501.317626953125,
|
| 6 |
+
"eval_logps/rejected": -525.1184692382812,
|
| 7 |
+
"eval_loss": 0.5698248147964478,
|
| 8 |
+
"eval_rewards/accuracies": 0.7460317611694336,
|
| 9 |
+
"eval_rewards/chosen": -1.5248812437057495,
|
| 10 |
+
"eval_rewards/margins": 0.6601181030273438,
|
| 11 |
+
"eval_rewards/rejected": -2.1849992275238037,
|
| 12 |
+
"eval_runtime": 235.0993,
|
| 13 |
+
"eval_samples": 2000,
|
| 14 |
+
"eval_samples_per_second": 8.507,
|
| 15 |
+
"eval_steps_per_second": 0.268,
|
| 16 |
+
"train_loss": 0.5349331027425397,
|
| 17 |
+
"train_runtime": 76573.4202,
|
| 18 |
+
"train_samples": 61135,
|
| 19 |
+
"train_samples_per_second": 3.992,
|
| 20 |
+
"train_steps_per_second": 0.062
|
| 21 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_logits/chosen": -1.8205610513687134,
|
| 4 |
+
"eval_logits/rejected": -1.714389681816101,
|
| 5 |
+
"eval_logps/chosen": -501.317626953125,
|
| 6 |
+
"eval_logps/rejected": -525.1184692382812,
|
| 7 |
+
"eval_loss": 0.5698248147964478,
|
| 8 |
+
"eval_rewards/accuracies": 0.7460317611694336,
|
| 9 |
+
"eval_rewards/chosen": -1.5248812437057495,
|
| 10 |
+
"eval_rewards/margins": 0.6601181030273438,
|
| 11 |
+
"eval_rewards/rejected": -2.1849992275238037,
|
| 12 |
+
"eval_runtime": 235.0993,
|
| 13 |
+
"eval_samples": 2000,
|
| 14 |
+
"eval_samples_per_second": 8.507,
|
| 15 |
+
"eval_steps_per_second": 0.268
|
| 16 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.36.2",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc398fe64f8c6317f7639e870e9931cbceb2794eb3dad09afd69b7cb055230d1
|
| 3 |
+
size 4984275728
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cf93093cab58eab7dfd460dcd8050a417cb7194cbfdb1df4d0726bff2cfcf23
|
| 3 |
+
size 4991625072
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33099d528559821e45b7dff19ed4af3df64b9cef0d112238b1c0ff4eead3fdf4
|
| 3 |
+
size 2882730416
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,692 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 12858544128
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 8 |
+
"model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 39 |
+
"model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
|
| 45 |
+
"model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00003.safetensors",
|
| 46 |
+
"model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors",
|
| 47 |
+
"model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00003.safetensors",
|
| 50 |
+
"model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00003.safetensors",
|
| 51 |
+
"model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00003.safetensors",
|
| 52 |
+
"model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00003.safetensors",
|
| 54 |
+
"model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00003.safetensors",
|
| 56 |
+
"model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00003.safetensors",
|
| 57 |
+
"model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00003.safetensors",
|
| 58 |
+
"model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00003.safetensors",
|
| 59 |
+
"model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00003.safetensors",
|
| 60 |
+
"model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00003.safetensors",
|
| 61 |
+
"model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00003.safetensors",
|
| 62 |
+
"model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00003.safetensors",
|
| 63 |
+
"model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
|
| 64 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 65 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 66 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 68 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 70 |
+
"model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00003.safetensors",
|
| 154 |
+
"model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00003.safetensors",
|
| 155 |
+
"model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00003.safetensors",
|
| 156 |
+
"model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
|
| 157 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 158 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 159 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 160 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 161 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 162 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 163 |
+
"model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
|
| 164 |
+
"model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
|
| 165 |
+
"model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00003.safetensors",
|
| 174 |
+
"model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00003.safetensors",
|
| 176 |
+
"model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00003.safetensors",
|
| 178 |
+
"model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00003.safetensors",
|
| 185 |
+
"model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00003.safetensors",
|
| 186 |
+
"model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"model.layers.13.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
|
| 188 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 193 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
|
| 195 |
+
"model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
|
| 197 |
+
"model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
|
| 198 |
+
"model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
|
| 199 |
+
"model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00003.safetensors",
|
| 216 |
+
"model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00003.safetensors",
|
| 217 |
+
"model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00003.safetensors",
|
| 218 |
+
"model.layers.14.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
|
| 219 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 220 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 221 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 222 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 223 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 224 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 225 |
+
"model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
|
| 231 |
+
"model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00003.safetensors",
|
| 234 |
+
"model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00003.safetensors",
|
| 235 |
+
"model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00003.safetensors",
|
| 236 |
+
"model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00003.safetensors",
|
| 237 |
+
"model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00003.safetensors",
|
| 238 |
+
"model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00003.safetensors",
|
| 243 |
+
"model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00003.safetensors",
|
| 245 |
+
"model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00003.safetensors",
|
| 246 |
+
"model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00003.safetensors",
|
| 247 |
+
"model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00003.safetensors",
|
| 248 |
+
"model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00003.safetensors",
|
| 249 |
+
"model.layers.15.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
|
| 250 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 251 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 252 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 253 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 254 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 255 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 256 |
+
"model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
|
| 258 |
+
"model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
|
| 260 |
+
"model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
|
| 261 |
+
"model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
|
| 262 |
+
"model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors",
|
| 263 |
+
"model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors",
|
| 264 |
+
"model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00003.safetensors",
|
| 265 |
+
"model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00003.safetensors",
|
| 266 |
+
"model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00003.safetensors",
|
| 267 |
+
"model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00003.safetensors",
|
| 268 |
+
"model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00003.safetensors",
|
| 269 |
+
"model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00003.safetensors",
|
| 270 |
+
"model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00003.safetensors",
|
| 271 |
+
"model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00003.safetensors",
|
| 272 |
+
"model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00003.safetensors",
|
| 273 |
+
"model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00003.safetensors",
|
| 274 |
+
"model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00003.safetensors",
|
| 275 |
+
"model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00003.safetensors",
|
| 276 |
+
"model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00003.safetensors",
|
| 277 |
+
"model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00003.safetensors",
|
| 278 |
+
"model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00003.safetensors",
|
| 279 |
+
"model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00003.safetensors",
|
| 280 |
+
"model.layers.16.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
|
| 281 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 282 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 283 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 284 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 285 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 286 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 287 |
+
"model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
|
| 288 |
+
"model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
|
| 289 |
+
"model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
|
| 290 |
+
"model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
|
| 291 |
+
"model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
|
| 292 |
+
"model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
|
| 293 |
+
"model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors",
|
| 294 |
+
"model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00003.safetensors",
|
| 295 |
+
"model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00003.safetensors",
|
| 296 |
+
"model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00003.safetensors",
|
| 297 |
+
"model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.layers.17.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
|
| 312 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 315 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 316 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 317 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 318 |
+
"model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
|
| 321 |
+
"model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
|
| 322 |
+
"model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
|
| 323 |
+
"model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
|
| 324 |
+
"model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors",
|
| 325 |
+
"model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00003.safetensors",
|
| 326 |
+
"model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00003.safetensors",
|
| 327 |
+
"model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00003.safetensors",
|
| 328 |
+
"model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00003.safetensors",
|
| 329 |
+
"model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00003.safetensors",
|
| 330 |
+
"model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00003.safetensors",
|
| 331 |
+
"model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00003.safetensors",
|
| 332 |
+
"model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00003.safetensors",
|
| 333 |
+
"model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00003.safetensors",
|
| 334 |
+
"model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00003.safetensors",
|
| 335 |
+
"model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00003.safetensors",
|
| 336 |
+
"model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00003.safetensors",
|
| 337 |
+
"model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00003.safetensors",
|
| 338 |
+
"model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00003.safetensors",
|
| 339 |
+
"model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00003.safetensors",
|
| 340 |
+
"model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00003.safetensors",
|
| 341 |
+
"model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00003.safetensors",
|
| 342 |
+
"model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
|
| 343 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 344 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 345 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 346 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00003.safetensors",
|
| 370 |
+
"model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00003.safetensors",
|
| 371 |
+
"model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00003.safetensors",
|
| 372 |
+
"model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00003.safetensors",
|
| 373 |
+
"model.layers.19.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
|
| 374 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 375 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 376 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 377 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 378 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 379 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 380 |
+
"model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
|
| 381 |
+
"model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
|
| 382 |
+
"model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
|
| 383 |
+
"model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
|
| 384 |
+
"model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
|
| 385 |
+
"model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
|
| 386 |
+
"model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00003.safetensors",
|
| 387 |
+
"model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors",
|
| 388 |
+
"model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors",
|
| 389 |
+
"model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00003.safetensors",
|
| 390 |
+
"model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00003.safetensors",
|
| 391 |
+
"model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00003.safetensors",
|
| 392 |
+
"model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00003.safetensors",
|
| 393 |
+
"model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00003.safetensors",
|
| 394 |
+
"model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00003.safetensors",
|
| 395 |
+
"model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00003.safetensors",
|
| 396 |
+
"model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00003.safetensors",
|
| 397 |
+
"model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00003.safetensors",
|
| 398 |
+
"model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00003.safetensors",
|
| 399 |
+
"model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00003.safetensors",
|
| 400 |
+
"model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00003.safetensors",
|
| 401 |
+
"model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00003.safetensors",
|
| 402 |
+
"model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00003.safetensors",
|
| 403 |
+
"model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00003.safetensors",
|
| 404 |
+
"model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
|
| 405 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 406 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 407 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 408 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 409 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 410 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 411 |
+
"model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
|
| 412 |
+
"model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
|
| 413 |
+
"model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
|
| 414 |
+
"model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
|
| 415 |
+
"model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
|
| 416 |
+
"model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
|
| 417 |
+
"model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors",
|
| 418 |
+
"model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00003.safetensors",
|
| 419 |
+
"model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00003.safetensors",
|
| 420 |
+
"model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00003.safetensors",
|
| 421 |
+
"model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00003.safetensors",
|
| 422 |
+
"model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00003.safetensors",
|
| 423 |
+
"model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00003.safetensors",
|
| 424 |
+
"model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00003.safetensors",
|
| 425 |
+
"model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00003.safetensors",
|
| 426 |
+
"model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00003.safetensors",
|
| 427 |
+
"model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00003.safetensors",
|
| 428 |
+
"model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00003.safetensors",
|
| 429 |
+
"model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00003.safetensors",
|
| 430 |
+
"model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00003.safetensors",
|
| 431 |
+
"model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00003.safetensors",
|
| 432 |
+
"model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00003.safetensors",
|
| 433 |
+
"model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00003.safetensors",
|
| 434 |
+
"model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00003.safetensors",
|
| 435 |
+
"model.layers.20.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
|
| 436 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 437 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 438 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 439 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 440 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 441 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 442 |
+
"model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
|
| 443 |
+
"model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
|
| 444 |
+
"model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
|
| 445 |
+
"model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
|
| 446 |
+
"model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
|
| 447 |
+
"model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
|
| 448 |
+
"model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors",
|
| 449 |
+
"model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00003.safetensors",
|
| 450 |
+
"model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00003.safetensors",
|
| 451 |
+
"model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00003.safetensors",
|
| 452 |
+
"model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00003.safetensors",
|
| 453 |
+
"model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00003.safetensors",
|
| 454 |
+
"model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00003.safetensors",
|
| 455 |
+
"model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00003.safetensors",
|
| 456 |
+
"model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00003.safetensors",
|
| 457 |
+
"model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00003.safetensors",
|
| 458 |
+
"model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00003.safetensors",
|
| 459 |
+
"model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00003.safetensors",
|
| 460 |
+
"model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00003.safetensors",
|
| 461 |
+
"model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00003.safetensors",
|
| 462 |
+
"model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00003.safetensors",
|
| 463 |
+
"model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00003.safetensors",
|
| 464 |
+
"model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00003.safetensors",
|
| 465 |
+
"model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00003.safetensors",
|
| 466 |
+
"model.layers.21.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
|
| 467 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 468 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 469 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 470 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 471 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 472 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 473 |
+
"model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
|
| 474 |
+
"model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
|
| 475 |
+
"model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
|
| 476 |
+
"model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
|
| 477 |
+
"model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
|
| 478 |
+
"model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
|
| 479 |
+
"model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00003.safetensors",
|
| 480 |
+
"model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors",
|
| 481 |
+
"model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors",
|
| 482 |
+
"model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00003.safetensors",
|
| 483 |
+
"model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00003.safetensors",
|
| 484 |
+
"model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00003.safetensors",
|
| 485 |
+
"model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00003.safetensors",
|
| 486 |
+
"model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00003.safetensors",
|
| 487 |
+
"model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00003.safetensors",
|
| 488 |
+
"model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00003.safetensors",
|
| 489 |
+
"model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00003.safetensors",
|
| 490 |
+
"model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00003.safetensors",
|
| 491 |
+
"model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00003.safetensors",
|
| 492 |
+
"model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00003.safetensors",
|
| 493 |
+
"model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00003.safetensors",
|
| 494 |
+
"model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00003.safetensors",
|
| 495 |
+
"model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00003.safetensors",
|
| 496 |
+
"model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00003.safetensors",
|
| 497 |
+
"model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
|
| 498 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 499 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 500 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 501 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 502 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 503 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 504 |
+
"model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
|
| 505 |
+
"model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
|
| 506 |
+
"model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
|
| 507 |
+
"model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
|
| 508 |
+
"model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
|
| 509 |
+
"model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
|
| 510 |
+
"model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00003.safetensors",
|
| 511 |
+
"model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors",
|
| 512 |
+
"model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors",
|
| 513 |
+
"model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00003.safetensors",
|
| 514 |
+
"model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00003.safetensors",
|
| 515 |
+
"model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00003.safetensors",
|
| 516 |
+
"model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00003.safetensors",
|
| 517 |
+
"model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00003.safetensors",
|
| 518 |
+
"model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00003.safetensors",
|
| 519 |
+
"model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00003.safetensors",
|
| 520 |
+
"model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00003.safetensors",
|
| 521 |
+
"model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00003.safetensors",
|
| 522 |
+
"model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00003.safetensors",
|
| 523 |
+
"model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00003.safetensors",
|
| 524 |
+
"model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00003.safetensors",
|
| 525 |
+
"model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00003.safetensors",
|
| 526 |
+
"model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00003.safetensors",
|
| 527 |
+
"model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00003.safetensors",
|
| 528 |
+
"model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
|
| 529 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 530 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 531 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 532 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 533 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 534 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 535 |
+
"model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
|
| 536 |
+
"model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
|
| 537 |
+
"model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
|
| 538 |
+
"model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
|
| 539 |
+
"model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
|
| 540 |
+
"model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
|
| 541 |
+
"model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00003.safetensors",
|
| 542 |
+
"model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors",
|
| 543 |
+
"model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors",
|
| 544 |
+
"model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00003.safetensors",
|
| 545 |
+
"model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00003.safetensors",
|
| 546 |
+
"model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00003.safetensors",
|
| 547 |
+
"model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00003.safetensors",
|
| 548 |
+
"model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00003.safetensors",
|
| 549 |
+
"model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00003.safetensors",
|
| 550 |
+
"model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00003.safetensors",
|
| 551 |
+
"model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00003.safetensors",
|
| 552 |
+
"model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00003.safetensors",
|
| 553 |
+
"model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00003.safetensors",
|
| 554 |
+
"model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00003.safetensors",
|
| 555 |
+
"model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00003.safetensors",
|
| 556 |
+
"model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00003.safetensors",
|
| 557 |
+
"model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00003.safetensors",
|
| 558 |
+
"model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00003.safetensors",
|
| 559 |
+
"model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
|
| 560 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 561 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 562 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 563 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 564 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 565 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 566 |
+
"model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
|
| 567 |
+
"model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
|
| 568 |
+
"model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
|
| 569 |
+
"model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
|
| 570 |
+
"model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
|
| 571 |
+
"model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
|
| 572 |
+
"model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00003.safetensors",
|
| 573 |
+
"model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors",
|
| 574 |
+
"model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors",
|
| 575 |
+
"model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00003.safetensors",
|
| 576 |
+
"model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00003.safetensors",
|
| 577 |
+
"model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00003.safetensors",
|
| 578 |
+
"model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00003.safetensors",
|
| 579 |
+
"model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00003.safetensors",
|
| 580 |
+
"model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00003.safetensors",
|
| 581 |
+
"model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00003.safetensors",
|
| 582 |
+
"model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00003.safetensors",
|
| 583 |
+
"model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00003.safetensors",
|
| 584 |
+
"model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00003.safetensors",
|
| 585 |
+
"model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00003.safetensors",
|
| 586 |
+
"model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00003.safetensors",
|
| 587 |
+
"model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00003.safetensors",
|
| 588 |
+
"model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00003.safetensors",
|
| 589 |
+
"model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00003.safetensors",
|
| 590 |
+
"model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
|
| 591 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 592 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 593 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 594 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 595 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 596 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 597 |
+
"model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
|
| 598 |
+
"model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
|
| 599 |
+
"model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
|
| 600 |
+
"model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
|
| 601 |
+
"model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
|
| 602 |
+
"model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
|
| 603 |
+
"model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00003.safetensors",
|
| 604 |
+
"model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors",
|
| 605 |
+
"model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors",
|
| 606 |
+
"model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00003.safetensors",
|
| 607 |
+
"model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00003.safetensors",
|
| 608 |
+
"model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00003.safetensors",
|
| 609 |
+
"model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00003.safetensors",
|
| 610 |
+
"model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00003.safetensors",
|
| 611 |
+
"model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00003.safetensors",
|
| 612 |
+
"model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00003.safetensors",
|
| 613 |
+
"model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00003.safetensors",
|
| 614 |
+
"model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00003.safetensors",
|
| 615 |
+
"model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00003.safetensors",
|
| 616 |
+
"model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00003.safetensors",
|
| 617 |
+
"model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00003.safetensors",
|
| 618 |
+
"model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00003.safetensors",
|
| 619 |
+
"model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00003.safetensors",
|
| 620 |
+
"model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00003.safetensors",
|
| 621 |
+
"model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
|
| 622 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 623 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 624 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 625 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 626 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 627 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 628 |
+
"model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
|
| 629 |
+
"model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
|
| 630 |
+
"model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
|
| 631 |
+
"model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
|
| 632 |
+
"model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
|
| 633 |
+
"model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
|
| 634 |
+
"model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00003.safetensors",
|
| 635 |
+
"model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors",
|
| 636 |
+
"model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors",
|
| 637 |
+
"model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00003.safetensors",
|
| 638 |
+
"model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00003.safetensors",
|
| 639 |
+
"model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00003.safetensors",
|
| 640 |
+
"model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00003.safetensors",
|
| 641 |
+
"model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00003.safetensors",
|
| 642 |
+
"model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00003.safetensors",
|
| 643 |
+
"model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00003.safetensors",
|
| 644 |
+
"model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00003.safetensors",
|
| 645 |
+
"model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00003.safetensors",
|
| 646 |
+
"model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00003.safetensors",
|
| 647 |
+
"model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00003.safetensors",
|
| 648 |
+
"model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00003.safetensors",
|
| 649 |
+
"model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00003.safetensors",
|
| 650 |
+
"model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00003.safetensors",
|
| 651 |
+
"model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00003.safetensors",
|
| 652 |
+
"model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
|
| 653 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 654 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 655 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 656 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 657 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 658 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 659 |
+
"model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
|
| 660 |
+
"model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
|
| 661 |
+
"model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
|
| 662 |
+
"model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
|
| 663 |
+
"model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
|
| 664 |
+
"model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
|
| 665 |
+
"model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors",
|
| 666 |
+
"model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors",
|
| 667 |
+
"model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00003.safetensors",
|
| 668 |
+
"model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00003.safetensors",
|
| 669 |
+
"model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00003.safetensors",
|
| 670 |
+
"model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00003.safetensors",
|
| 671 |
+
"model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00003.safetensors",
|
| 672 |
+
"model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00003.safetensors",
|
| 673 |
+
"model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00003.safetensors",
|
| 674 |
+
"model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00003.safetensors",
|
| 675 |
+
"model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00003.safetensors",
|
| 676 |
+
"model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00003.safetensors",
|
| 677 |
+
"model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00003.safetensors",
|
| 678 |
+
"model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00003.safetensors",
|
| 679 |
+
"model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00003.safetensors",
|
| 680 |
+
"model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00003.safetensors",
|
| 681 |
+
"model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00003.safetensors",
|
| 682 |
+
"model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00003.safetensors",
|
| 683 |
+
"model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
|
| 684 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 685 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 686 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 687 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 688 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 689 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 690 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 691 |
+
}
|
| 692 |
+
}
|
runs/Jan16_11-23-05_main1/events.out.tfevents.1705404271.main1.10305.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d42900fbff042679e10398e992c47cf2b5aa9202165b4df3128cf9837d50b8f6
|
| 3 |
+
size 342847
|
runs/Jan16_11-23-05_main1/events.out.tfevents.1705481079.main1.10305.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0be31e085c566e90dae6ccddf4638e31a4685e34a432628d2c1967953607149e
|
| 3 |
+
size 828
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.5349331027425397,
|
| 4 |
+
"train_runtime": 76573.4202,
|
| 5 |
+
"train_samples": 61135,
|
| 6 |
+
"train_samples_per_second": 3.992,
|
| 7 |
+
"train_steps_per_second": 0.062
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|