tzartrooper
commited on
Commit
•
2edd4a9
1
Parent(s):
0784930
Upload tokenizer
Browse files- README.md +1 -1
- added_tokens.json +3 -0
- special_tokens_map.json +14 -2
- tokenizer.json +10 -1
- tokenizer_config.json +10 -2
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: distilbert/distilgpt2
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
model-index:
|
7 |
- name: medical_chatbot_ruslanmv_ai-medical-chatbot
|
8 |
results: []
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
base_model: distilbert/distilgpt2
|
6 |
model-index:
|
7 |
- name: medical_chatbot_ruslanmv_ai-medical-chatbot
|
8 |
results: []
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|startoftext|>": 50257
|
3 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,6 +1,18 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"pad_token": "<|endoftext|>",
|
5 |
"unk_token": "<|endoftext|>"
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
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 |
"pad_token": "<|endoftext|>",
|
17 |
"unk_token": "<|endoftext|>"
|
18 |
}
|
tokenizer.json
CHANGED
@@ -9,7 +9,16 @@
|
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
-
"normalized":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
"special": true
|
14 |
}
|
15 |
],
|
|
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 50257,
|
17 |
+
"content": "<|startoftext|>",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
"special": true
|
23 |
}
|
24 |
],
|
tokenizer_config.json
CHANGED
@@ -4,13 +4,21 @@
|
|
4 |
"50256": {
|
5 |
"content": "<|endoftext|>",
|
6 |
"lstrip": false,
|
7 |
-
"normalized":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
}
|
12 |
},
|
13 |
-
"bos_token": "<|
|
14 |
"clean_up_tokenization_spaces": true,
|
15 |
"eos_token": "<|endoftext|>",
|
16 |
"model_max_length": 1024,
|
|
|
4 |
"50256": {
|
5 |
"content": "<|endoftext|>",
|
6 |
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"50257": {
|
13 |
+
"content": "<|startoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
}
|
20 |
},
|
21 |
+
"bos_token": "<|startoftext|>",
|
22 |
"clean_up_tokenization_spaces": true,
|
23 |
"eos_token": "<|endoftext|>",
|
24 |
"model_max_length": 1024,
|