mofawzy commited on
Commit
dbdea06
1 Parent(s): f6fac6d

first version of sentence generator for arabic language using gpt-2

Browse files
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "gradient_checkpointing": false,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "resid_pdrop": 0.1,
21
+ "summary_activation": null,
22
+ "summary_first_dropout": 0.1,
23
+ "summary_proj_to_labels": true,
24
+ "summary_type": "cls_index",
25
+ "summary_use_proj": true,
26
+ "vocab_size": 50000
27
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acbab758a860f54c6b2dcd9f0f681383a4c5ef8a1641d056216e626b62729336
3
+ size 509586767
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>"}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a74c51394d364b351c2d9ede44dfb9fb0ec97502746462e90a01d5c13326e33
3
+ size 497144144
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"special_tokens_map_file": null, "full_tokenizer_file": null}
vocab.json ADDED
The diff for this file is too large to render. See raw diff