Randolphzeng
commited on
Commit
•
53adc0a
1
Parent(s):
f741a32
Upload 4 files
Browse files- config.json +28 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"embd_pdrop": 0.1,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"layer_norm_epsilon": 1e-05,
|
11 |
+
"model_type": "gpt2",
|
12 |
+
"n_ctx": 1024,
|
13 |
+
"n_embd": 768,
|
14 |
+
"n_head": 12,
|
15 |
+
"n_inner": null,
|
16 |
+
"n_layer": 12,
|
17 |
+
"n_positions": 1024,
|
18 |
+
"output_past": true,
|
19 |
+
"resid_pdrop": 0.1,
|
20 |
+
"task_specific_params": {
|
21 |
+
"text-generation": {
|
22 |
+
"do_sample": true,
|
23 |
+
"max_length": 320
|
24 |
+
}
|
25 |
+
},
|
26 |
+
"tokenizer_class": "BertTokenizer",
|
27 |
+
"vocab_size": 21128
|
28 |
+
}
|
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": false, "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": 1024}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|