Commit
•
2bc3472
1
Parent(s):
114a675
GPT2-Tamil (#1)
Browse files- GPT2 Tamil (7d8f070a327c7585ecc881cd90eb8c4598551bed)
Co-authored-by: Muhammed Ashiq Abdul Khader <[email protected]>
- added_tokens.json +3 -0
- config.json +30 -0
- merges.txt +0 -0
- special_tokens_map.json +7 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +33 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 50000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"layer_norm_epsilon": 1e-05,
|
12 |
+
"model_type": "gpt2",
|
13 |
+
"n_embd": 768,
|
14 |
+
"n_head": 12,
|
15 |
+
"n_inner": null,
|
16 |
+
"n_layer": 12,
|
17 |
+
"n_positions": 1024,
|
18 |
+
"reorder_and_upcast_attn": false,
|
19 |
+
"resid_pdrop": 0.1,
|
20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
21 |
+
"scale_attn_weights": true,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"transformers_version": "4.20.1",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 50000
|
30 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd1cee47630bef12978644bfeccd41e185252ae34f2326c1148bad7afd295a37
|
3 |
+
size 497145392
|
tokenizer_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"name_or_path": "/kaggle/working/tokenized_data",
|
22 |
+
"pad_token": null,
|
23 |
+
"special_tokens_map_file": null,
|
24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "[UNK]",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|