Upload 9 files
Browse files- config.json +1 -1
- model.safetensors +1 -1
- special_tokens_map.json +3 -21
- tokenizer (1).json +2 -2
- tokenizer_config.json +0 -3
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "dbmdz/german-gpt2",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497798784
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:493802ff4be54bd2c80290c895426afaa073b7525ecc0e73fc151f6ac180b0d5
|
3 |
size 497798784
|
special_tokens_map.json
CHANGED
@@ -1,23 +1,5 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"unk_token": {
|
17 |
-
"content": "<|endoftext|>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
}
|
23 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|
tokenizer (1).json
CHANGED
@@ -81,8 +81,8 @@
|
|
81 |
"type": "BPE",
|
82 |
"dropout": null,
|
83 |
"unk_token": null,
|
84 |
-
"continuing_subword_prefix":
|
85 |
-
"end_of_word_suffix":
|
86 |
"fuse_unk": false,
|
87 |
"byte_fallback": false,
|
88 |
"vocab": {
|
|
|
81 |
"type": "BPE",
|
82 |
"dropout": null,
|
83 |
"unk_token": null,
|
84 |
+
"continuing_subword_prefix": null,
|
85 |
+
"end_of_word_suffix": null,
|
86 |
"fuse_unk": false,
|
87 |
"byte_fallback": false,
|
88 |
"vocab": {
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": false,
|
3 |
"add_prefix_space": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
@@ -54,9 +53,7 @@
|
|
54 |
"bos_token": "<|endoftext|>",
|
55 |
"clean_up_tokenization_spaces": true,
|
56 |
"eos_token": "<|endoftext|>",
|
57 |
-
"errors": "replace",
|
58 |
"model_max_length": 1000000000000000019884624838656,
|
59 |
-
"pad_token": null,
|
60 |
"tokenizer_class": "GPT2Tokenizer",
|
61 |
"unk_token": "<|endoftext|>"
|
62 |
}
|
|
|
1 |
{
|
|
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
|
|
53 |
"bos_token": "<|endoftext|>",
|
54 |
"clean_up_tokenization_spaces": true,
|
55 |
"eos_token": "<|endoftext|>",
|
|
|
56 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
57 |
"tokenizer_class": "GPT2Tokenizer",
|
58 |
"unk_token": "<|endoftext|>"
|
59 |
}
|