Model save
Browse files- README.md +100 -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/Jan22_17-48-19_main1/events.out.tfevents.1705946280.main1.2220.0 +2 -2
- runs/Jan22_17-48-19_main1/events.out.tfevents.1705993981.main1.2220.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: ondevicellm/tinyllama_moe_sft_ultrachat200k_v2_epochs3
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- dpo
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: tinyllama_moe_dpo_ultrachat_v2_epochs3
|
| 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_ultrachat_v2_epochs3
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [ondevicellm/tinyllama_moe_sft_ultrachat200k_v2_epochs3](https://huggingface.co/ondevicellm/tinyllama_moe_sft_ultrachat200k_v2_epochs3) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5855
|
| 21 |
+
- Rewards/chosen: -0.9040
|
| 22 |
+
- Rewards/rejected: -1.3959
|
| 23 |
+
- Rewards/accuracies: 0.7262
|
| 24 |
+
- Rewards/margins: 0.4918
|
| 25 |
+
- Logps/rejected: -442.2930
|
| 26 |
+
- Logps/chosen: -435.4489
|
| 27 |
+
- Logits/rejected: -2.3585
|
| 28 |
+
- Logits/chosen: -2.4345
|
| 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: 3
|
| 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 |
+
| 0.6914 | 0.1 | 100 | 0.6913 | 0.0043 | -0.0005 | 0.6349 | 0.0048 | -302.7554 | -344.6115 | -2.9876 | -3.0405 |
|
| 66 |
+
| 0.6836 | 0.21 | 200 | 0.6830 | 0.0149 | -0.0095 | 0.6448 | 0.0244 | -303.6508 | -343.5497 | -2.9700 | -3.0243 |
|
| 67 |
+
| 0.6662 | 0.31 | 300 | 0.6712 | -0.0134 | -0.0687 | 0.6746 | 0.0553 | -309.5701 | -346.3836 | -2.9423 | -2.9976 |
|
| 68 |
+
| 0.6538 | 0.42 | 400 | 0.6571 | -0.0814 | -0.1804 | 0.6766 | 0.0990 | -320.7438 | -353.1802 | -2.8979 | -2.9548 |
|
| 69 |
+
| 0.6405 | 0.52 | 500 | 0.6448 | -0.1949 | -0.3451 | 0.6726 | 0.1502 | -337.2181 | -364.5344 | -2.8541 | -2.9120 |
|
| 70 |
+
| 0.6394 | 0.63 | 600 | 0.6372 | -0.2303 | -0.4148 | 0.6825 | 0.1845 | -344.1863 | -368.0754 | -2.8147 | -2.8733 |
|
| 71 |
+
| 0.6218 | 0.73 | 700 | 0.6313 | -0.2894 | -0.5107 | 0.6825 | 0.2213 | -353.7792 | -373.9845 | -2.7666 | -2.8269 |
|
| 72 |
+
| 0.6035 | 0.84 | 800 | 0.6249 | -0.3614 | -0.6145 | 0.6845 | 0.2531 | -364.1536 | -381.1849 | -2.7056 | -2.7681 |
|
| 73 |
+
| 0.6326 | 0.94 | 900 | 0.6204 | -0.5259 | -0.8008 | 0.6845 | 0.2749 | -382.7857 | -397.6345 | -2.6568 | -2.7207 |
|
| 74 |
+
| 0.6103 | 1.05 | 1000 | 0.6145 | -0.5164 | -0.8178 | 0.6944 | 0.3014 | -384.4856 | -396.6823 | -2.6322 | -2.6969 |
|
| 75 |
+
| 0.6002 | 1.15 | 1100 | 0.6116 | -0.5179 | -0.8325 | 0.6925 | 0.3146 | -385.9578 | -396.8333 | -2.6024 | -2.6688 |
|
| 76 |
+
| 0.5729 | 1.26 | 1200 | 0.6083 | -0.5838 | -0.9200 | 0.7044 | 0.3362 | -394.7073 | -403.4271 | -2.5708 | -2.6376 |
|
| 77 |
+
| 0.599 | 1.36 | 1300 | 0.6077 | -0.5206 | -0.8453 | 0.7103 | 0.3247 | -387.2310 | -397.1021 | -2.5454 | -2.6134 |
|
| 78 |
+
| 0.5821 | 1.47 | 1400 | 0.6025 | -0.5941 | -0.9561 | 0.7063 | 0.3620 | -398.3106 | -404.4496 | -2.5211 | -2.5900 |
|
| 79 |
+
| 0.574 | 1.57 | 1500 | 0.5977 | -0.6617 | -1.0471 | 0.7143 | 0.3854 | -407.4162 | -411.2178 | -2.4887 | -2.5593 |
|
| 80 |
+
| 0.5716 | 1.67 | 1600 | 0.5955 | -0.6765 | -1.0870 | 0.7282 | 0.4105 | -411.4020 | -412.6956 | -2.4651 | -2.5369 |
|
| 81 |
+
| 0.5477 | 1.78 | 1700 | 0.5904 | -0.8020 | -1.2430 | 0.7321 | 0.4410 | -427.0003 | -425.2423 | -2.4342 | -2.5079 |
|
| 82 |
+
| 0.5718 | 1.88 | 1800 | 0.5898 | -0.7932 | -1.2439 | 0.7321 | 0.4507 | -427.0937 | -424.3631 | -2.4186 | -2.4928 |
|
| 83 |
+
| 0.563 | 1.99 | 1900 | 0.5904 | -0.6874 | -1.1313 | 0.7202 | 0.4439 | -415.8328 | -413.7807 | -2.4223 | -2.4961 |
|
| 84 |
+
| 0.5633 | 2.09 | 2000 | 0.5884 | -0.7564 | -1.2105 | 0.7262 | 0.4541 | -423.7504 | -420.6851 | -2.4073 | -2.4819 |
|
| 85 |
+
| 0.5564 | 2.2 | 2100 | 0.5878 | -0.8150 | -1.2802 | 0.7262 | 0.4652 | -430.7243 | -426.5488 | -2.3948 | -2.4696 |
|
| 86 |
+
| 0.5373 | 2.3 | 2200 | 0.5865 | -0.8791 | -1.3602 | 0.7341 | 0.4812 | -438.7289 | -432.9532 | -2.3795 | -2.4548 |
|
| 87 |
+
| 0.5559 | 2.41 | 2300 | 0.5872 | -0.8476 | -1.3260 | 0.7242 | 0.4784 | -435.3001 | -429.7996 | -2.3743 | -2.4496 |
|
| 88 |
+
| 0.5467 | 2.51 | 2400 | 0.5868 | -0.8483 | -1.3274 | 0.7222 | 0.4790 | -435.4401 | -429.8786 | -2.3697 | -2.4452 |
|
| 89 |
+
| 0.5666 | 2.62 | 2500 | 0.5858 | -0.8754 | -1.3626 | 0.7242 | 0.4872 | -438.9631 | -432.5811 | -2.3641 | -2.4399 |
|
| 90 |
+
| 0.5113 | 2.72 | 2600 | 0.5856 | -0.8942 | -1.3842 | 0.7242 | 0.4900 | -441.1211 | -434.4620 | -2.3604 | -2.4361 |
|
| 91 |
+
| 0.5601 | 2.83 | 2700 | 0.5855 | -0.9040 | -1.3959 | 0.7262 | 0.4918 | -442.2930 | -435.4489 | -2.3585 | -2.4345 |
|
| 92 |
+
| 0.5303 | 2.93 | 2800 | 0.5857 | -0.9003 | -1.3898 | 0.7242 | 0.4894 | -441.6805 | -435.0786 | -2.3581 | -2.4342 |
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
### Framework versions
|
| 96 |
+
|
| 97 |
+
- Transformers 4.36.2
|
| 98 |
+
- Pytorch 2.1.2+cu118
|
| 99 |
+
- Datasets 2.14.6
|
| 100 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_logits/chosen": -2.434546947479248,
|
| 4 |
+
"eval_logits/rejected": -2.35845685005188,
|
| 5 |
+
"eval_logps/chosen": -435.4488525390625,
|
| 6 |
+
"eval_logps/rejected": -442.29296875,
|
| 7 |
+
"eval_loss": 0.5855222344398499,
|
| 8 |
+
"eval_rewards/accuracies": 0.726190447807312,
|
| 9 |
+
"eval_rewards/chosen": -0.904042661190033,
|
| 10 |
+
"eval_rewards/margins": 0.49184030294418335,
|
| 11 |
+
"eval_rewards/rejected": -1.3958829641342163,
|
| 12 |
+
"eval_runtime": 247.0631,
|
| 13 |
+
"eval_samples": 2000,
|
| 14 |
+
"eval_samples_per_second": 8.095,
|
| 15 |
+
"eval_steps_per_second": 0.255,
|
| 16 |
+
"train_loss": 0.5928295368507478,
|
| 17 |
+
"train_runtime": 47453.5759,
|
| 18 |
+
"train_samples": 61135,
|
| 19 |
+
"train_samples_per_second": 3.865,
|
| 20 |
+
"train_steps_per_second": 0.06
|
| 21 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_logits/chosen": -2.434546947479248,
|
| 4 |
+
"eval_logits/rejected": -2.35845685005188,
|
| 5 |
+
"eval_logps/chosen": -435.4488525390625,
|
| 6 |
+
"eval_logps/rejected": -442.29296875,
|
| 7 |
+
"eval_loss": 0.5855222344398499,
|
| 8 |
+
"eval_rewards/accuracies": 0.726190447807312,
|
| 9 |
+
"eval_rewards/chosen": -0.904042661190033,
|
| 10 |
+
"eval_rewards/margins": 0.49184030294418335,
|
| 11 |
+
"eval_rewards/rejected": -1.3958829641342163,
|
| 12 |
+
"eval_runtime": 247.0631,
|
| 13 |
+
"eval_samples": 2000,
|
| 14 |
+
"eval_samples_per_second": 8.095,
|
| 15 |
+
"eval_steps_per_second": 0.255
|
| 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 sha256:8397226eaa246e663940f3ec27ef679392ce47b1b4334b731506b174b3faea0f
|
| 3 |
+
size 4984275728
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a2c3d5b2f0f9cc223c82ef716b94c2fd782d8a6c8dcb51985445faf171c9087
|
| 3 |
+
size 4991625072
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7777cb5f78168db249ce83e664ef3b4fd18d0d0d66179adb6e50099d8ec8ed1d
|
| 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/Jan22_17-48-19_main1/events.out.tfevents.1705946280.main1.2220.0
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 sha256:0856c643dd88c44637ad2e40821ff9c2a5b12cb7138cc3e777ec087f17a4e276
|
| 3 |
+
size 207708
|
runs/Jan22_17-48-19_main1/events.out.tfevents.1705993981.main1.2220.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9050bbfea14ac09a4f96b3c39d71f72e2fe4889c67fe9cb41fb195a7990b06c
|
| 3 |
+
size 828
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.5928295368507478,
|
| 4 |
+
"train_runtime": 47453.5759,
|
| 5 |
+
"train_samples": 61135,
|
| 6 |
+
"train_samples_per_second": 3.865,
|
| 7 |
+
"train_steps_per_second": 0.06
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|