koziev ilya commited on
Commit
1e50d38
1 Parent(s): c13cb6b

dataset cleanup and extension; model retrained

Browse files
added_tokens.json CHANGED
@@ -1 +1,3 @@
1
- {"<|endoftext|>": 50257}
 
 
 
1
+ {
2
+ "<|endoftext|>": 50257
3
+ }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/home/jovyan/rugpt3large_based_on_gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
@@ -18,7 +18,9 @@
18
  "n_inner": null,
19
  "n_layer": 24,
20
  "n_positions": 2048,
 
21
  "resid_pdrop": 0.1,
 
22
  "scale_attn_weights": true,
23
  "summary_activation": null,
24
  "summary_first_dropout": 0.1,
@@ -26,7 +28,7 @@
26
  "summary_type": "cls_index",
27
  "summary_use_proj": true,
28
  "torch_dtype": "float32",
29
- "transformers_version": "4.11.3",
30
  "use_cache": true,
31
  "vocab_size": 50258
32
  }
 
1
  {
2
+ "_name_or_path": "sberbank-ai/rugpt3large_based_on_gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
18
  "n_inner": null,
19
  "n_layer": 24,
20
  "n_positions": 2048,
21
+ "reorder_and_upcast_attn": false,
22
  "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
  "scale_attn_weights": true,
25
  "summary_activation": null,
26
  "summary_first_dropout": 0.1,
 
28
  "summary_type": "cls_index",
29
  "summary_use_proj": true,
30
  "torch_dtype": "float32",
31
+ "transformers_version": "4.21.1",
32
  "use_cache": true,
33
  "vocab_size": 50258
34
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7af95718330cadf66b203f528b7c9869490300c5a46307fe116a8d30b306d891
3
- size 3142000547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d1f018cf1d352b7ecb794dc46538bf16923bf52664ecce60554158a7ec6975d
3
+ size 3141981411
special_tokens_map.json CHANGED
@@ -1 +1,12 @@
1
- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<pad>"}
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ }
12
+ }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1,33 @@
1
- {"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, "special_tokens_map_file": null, "name_or_path": "/home/jovyan/rugpt3large_based_on_gpt2", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "sberbank-ai/rugpt3large_based_on_gpt2",
22
+ "pad_token": null,
23
+ "special_tokens_map_file": null,
24
+ "tokenizer_class": "GPT2Tokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }