Update README.md
Browse files
README.md
CHANGED
@@ -3,9 +3,18 @@ license: apache-2.0
|
|
3 |
base_model: Sakonii/distilgpt2-nepali
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
-
- name: distilgpt2-nepali-
|
8 |
results: []
|
|
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -19,18 +28,17 @@ It achieves the following results on the evaluation set:
|
|
19 |
|
20 |
## Model description
|
21 |
|
22 |
-
|
23 |
|
24 |
## Intended uses & limitations
|
25 |
|
26 |
-
|
27 |
-
|
28 |
-
## Training and evaluation data
|
29 |
-
|
30 |
-
More information needed
|
31 |
|
32 |
## Training procedure
|
33 |
|
|
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
@@ -58,4 +66,4 @@ The following hyperparameters were used during training:
|
|
58 |
- Transformers 4.32.1
|
59 |
- Pytorch 2.0.0
|
60 |
- Datasets 2.1.0
|
61 |
-
- Tokenizers 0.13.3
|
|
|
3 |
base_model: Sakonii/distilgpt2-nepali
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
widget:
|
7 |
+
- text: 'नेपाली राजनीतिमा युवा पिढीको भूमिका के हो? '
|
8 |
+
example_title: Example 1
|
9 |
+
- text: 'नेपालको ग्रामीण र शहरी क्षेत्रमा स्वास्थ्य सेवा कस्तो छ? '
|
10 |
+
example_title: Example 2
|
11 |
+
- text: 'नेपाली राजनीतिमा युवा पिढीको भूमिका के हो? '
|
12 |
+
example_title: Example 3
|
13 |
model-index:
|
14 |
+
- name: distilgpt2-nepali-qa
|
15 |
results: []
|
16 |
+
language:
|
17 |
+
- ne
|
18 |
---
|
19 |
|
20 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
28 |
|
29 |
## Model description
|
30 |
|
31 |
+
Refer to original [distilgpt2](https://huggingface.co/distilgpt2)
|
32 |
|
33 |
## Intended uses & limitations
|
34 |
|
35 |
+
This marginally fine-tuned model can be used for Nepali text generation and possibly question answering and intends to be fine-tuned on Nepali language focused generative downstream task.
|
36 |
+
The language model being trained on a data with texts grouped to a block size of 512, it handles text sequence up to 512 tokens.
|
|
|
|
|
|
|
37 |
|
38 |
## Training procedure
|
39 |
|
40 |
+
The model is trained with the same configuration as the original [distilgpt2](https://huggingface.co/distilgpt2); but with 512 tokens per instance, 72 instances per batch, and around 34.14K training steps (excluding the pre-training with CLM Objective).
|
41 |
+
|
42 |
### Training hyperparameters
|
43 |
|
44 |
The following hyperparameters were used during training:
|
|
|
66 |
- Transformers 4.32.1
|
67 |
- Pytorch 2.0.0
|
68 |
- Datasets 2.1.0
|
69 |
+
- Tokenizers 0.13.3
|