DavidLanz commited on
Commit
af9845c
1 Parent(s): f6c9f51

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
@@ -8,6 +8,7 @@
8
  "bos_token_id": 50256,
9
  "embd_pdrop": 0.1,
10
  "eos_token_id": 50256,
 
11
  "initializer_range": 0.02,
12
  "layer_norm_epsilon": 1e-05,
13
  "model_type": "gpt2",
@@ -17,6 +18,7 @@
17
  "n_inner": null,
18
  "n_layer": 12,
19
  "n_positions": 1024,
 
20
  "reorder_and_upcast_attn": false,
21
  "resid_pdrop": 0.1,
22
  "scale_attn_by_inverse_layer_idx": false,
@@ -29,11 +31,12 @@
29
  "task_specific_params": {
30
  "text-generation": {
31
  "do_sample": true,
32
- "max_length": 50
33
  }
34
  },
 
35
  "torch_dtype": "float32",
36
  "transformers_version": "4.29.2",
37
  "use_cache": true,
38
- "vocab_size": 50257
39
  }
 
1
  {
2
+ "_name_or_path": "uer/gpt2-chinese-cluecorpussmall",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
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,
14
  "model_type": "gpt2",
 
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
  "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
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bf5a211010cd5e5ccfd926b671dbd73cb5ff71d73aa5b76444910e319542770
3
- size 510400655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abdae1d20c2917b8fc88b1fef2e5adafc1fb5d26eb87e7c9a70ba6cb0757d620
3
+ size 420916367
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c21e45009ca596710dd3d96b3f447ece6734d31191dd4d92ed479ff4b6a4e92c
3
  size 3887
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cb760db60da9cd4c4db1919a21852e0d807555e21332417a61829b93385c547
3
  size 3887
vocab.txt ADDED
The diff for this file is too large to render. See raw diff