Update README.md
Browse files
README.md
CHANGED
@@ -1,30 +1,28 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
5 |
model-index:
|
6 |
- name: KoRWKV-6B-koalpaca-v1.1a
|
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 |
-
# KoRWKV-6B
|
14 |
|
15 |
-
This model is a fine-tuned version of [beomi/KoRWKV-6B](https://huggingface.co/beomi/KoRWKV-6B) on an
|
16 |
|
17 |
-
|
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 |
|
@@ -33,7 +31,6 @@ More information needed
|
|
33 |
The following hyperparameters were used during training:
|
34 |
- learning_rate: 2e-05
|
35 |
- train_batch_size: 1
|
36 |
-
- eval_batch_size: 8
|
37 |
- seed: 42
|
38 |
- gradient_accumulation_steps: 8
|
39 |
- total_train_batch_size: 8
|
@@ -41,14 +38,11 @@ The following hyperparameters were used during training:
|
|
41 |
- lr_scheduler_type: linear
|
42 |
- num_epochs: 1.0
|
43 |
- mixed_precision_training: Native AMP
|
44 |
-
|
45 |
-
### Training results
|
46 |
-
|
47 |
-
|
48 |
|
49 |
### Framework versions
|
50 |
|
51 |
- Transformers 4.29.2
|
52 |
- Pytorch 1.13.1
|
53 |
- Datasets 2.12.0
|
54 |
-
- Tokenizers 0.13.3
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
- KoRWKV
|
6 |
+
- KoAlpaca
|
7 |
model-index:
|
8 |
- name: KoRWKV-6B-koalpaca-v1.1a
|
9 |
results: []
|
10 |
+
datasets:
|
11 |
+
- beomi/KoAlpaca-v1.1a
|
12 |
+
language:
|
13 |
+
- ko
|
14 |
+
library_name: transformers
|
15 |
+
pipeline_tag: text-generation
|
16 |
---
|
17 |
|
18 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
19 |
should probably proofread and complete it, then remove this comment. -->
|
20 |
|
21 |
+
# KoAlpaca-KoRWKV-6B (v1.1a)
|
22 |
|
23 |
+
This model is a fine-tuned version of [beomi/KoRWKV-6B](https://huggingface.co/beomi/KoRWKV-6B) on an [KoAlpaca v1.1a Dataset](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a).
|
24 |
|
25 |
+
Detail Codes are available at [KoAlpaca Github Repository](https://github.com/Beomi/KoAlpaca)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
|
27 |
## Training procedure
|
28 |
|
|
|
31 |
The following hyperparameters were used during training:
|
32 |
- learning_rate: 2e-05
|
33 |
- train_batch_size: 1
|
|
|
34 |
- seed: 42
|
35 |
- gradient_accumulation_steps: 8
|
36 |
- total_train_batch_size: 8
|
|
|
38 |
- lr_scheduler_type: linear
|
39 |
- num_epochs: 1.0
|
40 |
- mixed_precision_training: Native AMP
|
41 |
+
- Trained on 1x H100(80G PCI-E) GPU
|
|
|
|
|
|
|
42 |
|
43 |
### Framework versions
|
44 |
|
45 |
- Transformers 4.29.2
|
46 |
- Pytorch 1.13.1
|
47 |
- Datasets 2.12.0
|
48 |
+
- Tokenizers 0.13.3
|