Upload folder using huggingface_hub
Browse files- ckpt.pt +3 -0
- tokenizer/added_tokens.json +7 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +6 -0
- tokenizer/tokenizer.json +0 -0
- tokenizer/tokenizer_config.json +61 -0
- tokenizer/vocab.json +0 -0
ckpt.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8971c8b3b55fcfeb8021b7356e60365a45e6b2dd745e2861d5ce4f2b5e91d29b
|
3 |
+
size 342380887
|
tokenizer/added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 50260,
|
3 |
+
"<|end_of_turn|>": 50258,
|
4 |
+
"<|start_of_turn|>": 50257,
|
5 |
+
"<|system|>": 50261,
|
6 |
+
"<|user|>": 50259
|
7 |
+
}
|
tokenizer/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"50257": {
|
13 |
+
"content": "<|start_of_turn|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": false
|
19 |
+
},
|
20 |
+
"50258": {
|
21 |
+
"content": "<|end_of_turn|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": false
|
27 |
+
},
|
28 |
+
"50259": {
|
29 |
+
"content": "<|user|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
},
|
36 |
+
"50260": {
|
37 |
+
"content": "<|assistant|>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": false
|
43 |
+
},
|
44 |
+
"50261": {
|
45 |
+
"content": "<|system|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
}
|
52 |
+
},
|
53 |
+
"bos_token": "<|endoftext|>",
|
54 |
+
"chat_template": "{{ bos_token }}\n{% for message in messages %}\n {% if (message['role'] != 'assistant' and message['role'] != 'user' and message['role'] != 'system') %}\n {{ raise_exception('Only user and assistant and system role are supported') }}\n {% endif %}\n {{ '<|start_of_turn|>' + '<|' + message['role'] + '|>'+ '\\n' + message['content'] | trim + '<|end_of_turn|>\\n' }}\n{% endfor %}\n{% if add_generation_prompt %}\n {{'<|start_of_turn|><|assistant|>\\n'}}\n{% endif %}",
|
55 |
+
"clean_up_tokenization_spaces": false,
|
56 |
+
"eos_token": "<|endoftext|>",
|
57 |
+
"model_max_length": 1024,
|
58 |
+
"pad_token": "<|endoftext|>",
|
59 |
+
"tokenizer_class": "GPT2Tokenizer",
|
60 |
+
"unk_token": "<|endoftext|>"
|
61 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|