cahya commited on
Commit
3af6689
·
1 Parent(s): 9d75d17

add model files

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|SEP|>": 50261, "<|EOS|>": 50258, "<|BOS|>": 50257, "<|PAD|>": 50260, "<|UNK|>": 50259}
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "indonesian-nlp/gpt2-medium-indonesian",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50257,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50258,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 1024,
17
+ "n_head": 16,
18
+ "n_inner": null,
19
+ "n_layer": 24,
20
+ "n_positions": 1024,
21
+ "n_special": 0,
22
+ "pad_token_id": 50260,
23
+ "predict_special_tokens": true,
24
+ "reorder_and_upcast_attn": false,
25
+ "resid_pdrop": 0.0,
26
+ "scale_attn_by_inverse_layer_idx": false,
27
+ "scale_attn_weights": true,
28
+ "sep_token_id": 50261,
29
+ "summary_activation": null,
30
+ "summary_first_dropout": 0.1,
31
+ "summary_proj_to_labels": true,
32
+ "summary_type": "cls_index",
33
+ "summary_use_proj": true,
34
+ "task_specific_params": {
35
+ "text-generation": {
36
+ "do_sample": true,
37
+ "max_length": 50
38
+ }
39
+ },
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.13.0",
42
+ "use_cache": true,
43
+ "vocab_size": 50262
44
+ }
emissions.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
2
+ 2022-06-03T20:38:32,0642b07f-6569-470d-bf82-3ef2acbb3a4d,codecarbon,23944.548701524734,4.227144515973051,7.899046412145306,Austria,AUT,vienna,N,,
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:fbed634e467f38bdd0d8119614da426c8085bf2b89f811ff34165be0c3438b88
3
+ size 1444601817
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|BOS|>", "eos_token": "<|EOS|>", "unk_token": "<|UNK|>", "sep_token": "<|SEP|>", "pad_token": "<|PAD|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "indonesian-nlp/gpt2-medium-indonesian", "tokenizer_class": "GPT2Tokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4fbc8b71f3029cfbf43c638755d83d6ae2943d0cefa40185d019afe4fc37f8
3
+ size 2991
vocab.json ADDED
The diff for this file is too large to render. See raw diff