Commit
•
285f466
0
Parent(s):
init
Browse files- .gitattributes +16 -0
- config.json +37 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
.gitattributes
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 101,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 102,
|
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 |
+
"tie_word_embeddings": false,
|
33 |
+
"tokenizer_class": "BertTokenizerFast",
|
34 |
+
"transformers_version": "4.5.1",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 21128
|
37 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ead48d6a1cd189178c396c2e6b859e4b78871970fb0c642608db2ab8cef15e6
|
3 |
+
size 485912852
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "ckiplab/gpt2-base-chinese", "special_tokens_map_file": "/root/.cache/huggingface/transformers/da2a6a6111a4fd14554e008b8b86a0655c8e5484fbc252508eeb51d7a7d57ef0.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "do_basic_tokenize": true, "never_split": null}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|