shahidul034
commited on
Commit
•
1f4de76
1
Parent(s):
e53b152
Upload model
Browse files- README.md +8 -14
- config.json +2 -2
- generation_config.json +6 -0
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -6,12 +6,13 @@ model-index:
|
|
6 |
results: []
|
7 |
---
|
8 |
|
9 |
-
|
|
|
10 |
|
11 |
# text_generation_bangla_model
|
12 |
|
13 |
-
This model was trained from scratch on
|
14 |
-
|
15 |
|
16 |
|
17 |
## Model description
|
@@ -29,13 +30,6 @@ More information needed
|
|
29 |
## Training procedure
|
30 |
|
31 |
### Training hyperparameters
|
32 |
-
Learning rate: 5e-5
|
33 |
-
num_warmup_steps: 1000
|
34 |
-
weight_decay_rate: 0.01
|
35 |
-
batch_size: 8
|
36 |
-
Trainable params: 124,439,808
|
37 |
-
|
38 |
-
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
- optimizer: None
|
@@ -47,7 +41,7 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
### Framework versions
|
49 |
|
50 |
-
- Transformers 4.
|
51 |
-
- TensorFlow 2.
|
52 |
-
- Datasets 2.
|
53 |
-
- Tokenizers 0.
|
|
|
6 |
results: []
|
7 |
---
|
8 |
|
9 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
10 |
+
probably proofread and complete it, then remove this comment. -->
|
11 |
|
12 |
# text_generation_bangla_model
|
13 |
|
14 |
+
This model was trained from scratch on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
|
17 |
|
18 |
## Model description
|
|
|
30 |
## Training procedure
|
31 |
|
32 |
### Training hyperparameters
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- optimizer: None
|
|
|
41 |
|
42 |
### Framework versions
|
43 |
|
44 |
+
- Transformers 4.26.1
|
45 |
+
- TensorFlow 2.11.0
|
46 |
+
- Datasets 2.10.0
|
47 |
+
- Tokenizers 0.13.2
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/content/drive/MyDrive/text generation model",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -34,7 +34,7 @@
|
|
34 |
}
|
35 |
},
|
36 |
"torch_dtype": "float32",
|
37 |
-
"transformers_version": "4.
|
38 |
"use_cache": true,
|
39 |
"vocab_size": 50257
|
40 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/content/drive/MyDrive/text generation model/pytorch model",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
34 |
}
|
35 |
},
|
36 |
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.26.1",
|
38 |
"use_cache": true,
|
39 |
"vocab_size": 50257
|
40 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.26.1"
|
6 |
+
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497935464
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d447109af3b01b776410a3ebc25c69f808d4efc3839016f4029574367cb9d3a3
|
3 |
size 497935464
|