Update README.md
Browse files
README.md
CHANGED
|
@@ -2,29 +2,23 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: polyglot-12.8b-koalpaca-v1.1b
|
| 7 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
|
| 13 |
# polyglot-12.8b-koalpaca-v1.1b
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) on
|
| 16 |
-
|
| 17 |
-
## Model description
|
| 18 |
-
|
| 19 |
-
More information needed
|
| 20 |
-
|
| 21 |
-
## Intended uses & limitations
|
| 22 |
-
|
| 23 |
-
More information needed
|
| 24 |
-
|
| 25 |
-
## Training and evaluation data
|
| 26 |
-
|
| 27 |
-
More information needed
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
|
@@ -35,7 +29,7 @@ The following hyperparameters were used during training:
|
|
| 35 |
- train_batch_size: 1
|
| 36 |
- eval_batch_size: 8
|
| 37 |
- seed: 42
|
| 38 |
-
- distributed_type: multi-GPU
|
| 39 |
- num_devices: 4
|
| 40 |
- gradient_accumulation_steps: 64
|
| 41 |
- total_train_batch_size: 256
|
|
@@ -44,13 +38,9 @@ The following hyperparameters were used during training:
|
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- num_epochs: 2.0
|
| 46 |
|
| 47 |
-
### Training results
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
### Framework versions
|
| 52 |
|
| 53 |
- Transformers 4.28.1
|
| 54 |
- Pytorch 2.0.0+cu117
|
| 55 |
- Datasets 2.11.0
|
| 56 |
-
- Tokenizers 0.13.3
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
- polyglot-ko
|
| 6 |
+
- gpt-neox
|
| 7 |
+
- KoAlpaca
|
| 8 |
model-index:
|
| 9 |
- name: polyglot-12.8b-koalpaca-v1.1b
|
| 10 |
results: []
|
| 11 |
+
language:
|
| 12 |
+
- ko
|
| 13 |
+
datasets:
|
| 14 |
+
- KoAlpaca-v1.1b
|
| 15 |
+
pipeline_tag: text-generation
|
| 16 |
---
|
| 17 |
|
|
|
|
|
|
|
| 18 |
|
| 19 |
# polyglot-12.8b-koalpaca-v1.1b
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) on a KoAlpaca Dataset v1.1b
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Training procedure
|
| 24 |
|
|
|
|
| 29 |
- train_batch_size: 1
|
| 30 |
- eval_batch_size: 8
|
| 31 |
- seed: 42
|
| 32 |
+
- distributed_type: multi-GPU (A100 80G)
|
| 33 |
- num_devices: 4
|
| 34 |
- gradient_accumulation_steps: 64
|
| 35 |
- total_train_batch_size: 256
|
|
|
|
| 38 |
- lr_scheduler_type: linear
|
| 39 |
- num_epochs: 2.0
|
| 40 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
### Framework versions
|
| 42 |
|
| 43 |
- Transformers 4.28.1
|
| 44 |
- Pytorch 2.0.0+cu117
|
| 45 |
- Datasets 2.11.0
|
| 46 |
+
- Tokenizers 0.13.3
|