DavidLanz commited on
Commit
125e91c
1 Parent(s): c6e0d58

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 101,
3
+ "[MASK]": 103,
4
+ "[PAD]": 0,
5
+ "[SEP]": 102,
6
+ "[UNK]": 100
7
+ }
config.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "_name_or_path": "uer/gpt2-chinese-cluecorpussmall",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
6
  ],
7
  "attn_pdrop": 0.1,
8
- "bos_token_id": 50256,
9
  "embd_pdrop": 0.1,
10
- "eos_token_id": 50256,
11
  "gradient_checkpointing": false,
12
  "initializer_range": 0.02,
13
  "layer_norm_epsilon": 1e-05,
@@ -18,7 +18,6 @@
18
  "n_inner": null,
19
  "n_layer": 12,
20
  "n_positions": 1024,
21
- "output_past": true,
22
  "reorder_and_upcast_attn": false,
23
  "resid_pdrop": 0.1,
24
  "scale_attn_by_inverse_layer_idx": false,
@@ -31,12 +30,12 @@
31
  "task_specific_params": {
32
  "text-generation": {
33
  "do_sample": true,
34
- "max_length": 320
35
  }
36
  },
37
- "tokenizer_class": "BertTokenizer",
38
  "torch_dtype": "float32",
39
- "transformers_version": "4.29.2",
40
  "use_cache": true,
41
  "vocab_size": 21128
42
  }
 
1
  {
2
+ "_name_or_path": "ckiplab/gpt2-base-chinese",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
6
  ],
7
  "attn_pdrop": 0.1,
8
+ "bos_token_id": 101,
9
  "embd_pdrop": 0.1,
10
+ "eos_token_id": 102,
11
  "gradient_checkpointing": false,
12
  "initializer_range": 0.02,
13
  "layer_norm_epsilon": 1e-05,
 
18
  "n_inner": null,
19
  "n_layer": 12,
20
  "n_positions": 1024,
 
21
  "reorder_and_upcast_attn": false,
22
  "resid_pdrop": 0.1,
23
  "scale_attn_by_inverse_layer_idx": false,
 
30
  "task_specific_params": {
31
  "text-generation": {
32
  "do_sample": true,
33
+ "max_length": 50
34
  }
35
  },
36
+ "tokenizer_class": "BertTokenizerFast",
37
  "torch_dtype": "float32",
38
+ "transformers_version": "4.34.0",
39
  "use_cache": true,
40
  "vocab_size": 21128
41
  }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
- "transformers_version": "4.29.2"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 101,
4
+ "eos_token_id": 102,
5
+ "transformers_version": "4.34.0"
6
  }
logs/events.out.tfevents.1697419532.85ab8e7ad7a7.172.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf94e039706415d93c0d0425dd0d7017683ed6893f22564f61ca3aeef6f7a86
3
+ size 5261
logs/events.out.tfevents.1697419615.85ab8e7ad7a7.172.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e879172e06556ef68bd24838494f6fc0165840f444b9db39eda39785ed3b270d
3
+ size 6368
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46e282756979aeab9bc09b49dc92196ea0ae52bdb18eb34f3c6d96e94df677c1
3
- size 420916367
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c1f9c8ebb17b732b55eda423b66013c829adc3ccb1f8b44470d038eb9c5d733
3
+ size 408322909
special_tokens_map.json CHANGED
@@ -1,4 +1,11 @@
1
  {
 
 
 
 
 
 
 
2
  "cls_token": "[CLS]",
3
  "mask_token": "[MASK]",
4
  "pad_token": "[PAD]",
 
1
  {
2
+ "additional_special_tokens": [
3
+ "[PAD]",
4
+ "[UNK]",
5
+ "[CLS]",
6
+ "[SEP]",
7
+ "[MASK]"
8
+ ],
9
  "cls_token": "[CLS]",
10
  "mask_token": "[MASK]",
11
  "pad_token": "[PAD]",
tokenizer_config.json CHANGED
@@ -1,15 +1,65 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
4
  "do_basic_tokenize": true,
5
- "do_lower_case": false,
6
  "mask_token": "[MASK]",
7
- "model_max_length": 1024,
8
  "never_split": null,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
11
  "strip_accents": null,
12
  "tokenize_chinese_chars": true,
13
  "tokenizer_class": "BertTokenizer",
 
14
  "unk_token": "[UNK]"
15
  }
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [
45
+ "[PAD]",
46
+ "[UNK]",
47
+ "[CLS]",
48
+ "[SEP]",
49
+ "[MASK]"
50
+ ],
51
  "clean_up_tokenization_spaces": true,
52
  "cls_token": "[CLS]",
53
  "do_basic_tokenize": true,
54
+ "do_lower_case": true,
55
  "mask_token": "[MASK]",
56
+ "model_max_length": 512,
57
  "never_split": null,
58
  "pad_token": "[PAD]",
59
  "sep_token": "[SEP]",
60
  "strip_accents": null,
61
  "tokenize_chinese_chars": true,
62
  "tokenizer_class": "BertTokenizer",
63
+ "tokenizer_file": null,
64
  "unk_token": "[UNK]"
65
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3df88026d021d252212dbbd9dc6aa0de08a4b048cbb999d85c83378f84000180
3
- size 3887
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56543dfb566f911345cfc01a5beb67e18ba2d5362107221622da8ab4efc5a1e4
3
+ size 4027