redrussianarmy commited on
Commit
76f7408
1 Parent(s): 3af9ee7

First version of the GPT2-Turkish

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
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
+ "task_specific_params": {
27
+ "text-generation": {
28
+ "do_sample": true,
29
+ "max_length": 50
30
+ }
31
+ },
32
+ "vocab_size": 50257
33
+ }
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 sha256:1c11264d48e8078c36f9decc41eff62fd905111237e2cd7d60651d9f94bb946f
3
+ size 510406550
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a4723564f63bbf7b892a5f305a7da2f615d61664796d8429bb82938eeea441f
3
+ size 497933648
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "tokenized_data/"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98dfdf111b52ba132eacb3565fd61dc1529f62b170c6ff6ed7fe5fee33eb501
3
+ size 1775
vocab.json ADDED
The diff for this file is too large to render. See raw diff