danielhanchen
commited on
Commit
•
2bc2f21
1
Parent(s):
89e4fd4
Update tokenizer_config.json
Browse files- tokenizer_config.json +47 -1
tokenizer_config.json
CHANGED
@@ -1,3 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"128000": {
|
@@ -2052,7 +2097,7 @@
|
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
-
"eos_token": "<|
|
2056 |
"model_input_names": [
|
2057 |
"input_ids",
|
2058 |
"attention_mask"
|
@@ -2062,3 +2107,4 @@
|
|
2062 |
"padding_side": "left",
|
2063 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2064 |
}
|
|
|
|
1 |
+
|
2 |
+
Hugging Face's logo Hugging Face
|
3 |
+
|
4 |
+
Models
|
5 |
+
Datasets
|
6 |
+
Spaces
|
7 |
+
Posts
|
8 |
+
Docs
|
9 |
+
Pricing
|
10 |
+
|
11 |
+
meta-llama
|
12 |
+
/
|
13 |
+
Meta-Llama-3-8B-Instruct
|
14 |
+
Text Generation
|
15 |
+
Transformers
|
16 |
+
Safetensors
|
17 |
+
PyTorch
|
18 |
+
English
|
19 |
+
llama
|
20 |
+
facebook
|
21 |
+
meta
|
22 |
+
llama-3
|
23 |
+
conversational
|
24 |
+
Inference Endpoints
|
25 |
+
text-generation-inference
|
26 |
+
Model card
|
27 |
+
Files and versions
|
28 |
+
Community
|
29 |
+
108
|
30 |
+
Meta-Llama-3-8B-Instruct
|
31 |
+
/ tokenizer_config.json
|
32 |
+
ArthurZ's picture
|
33 |
+
ArthurZ
|
34 |
+
HF staff
|
35 |
+
Update tokenizer_config.json (#60)
|
36 |
+
a897769
|
37 |
+
verified
|
38 |
+
5 days ago
|
39 |
+
raw
|
40 |
+
history
|
41 |
+
blame
|
42 |
+
contribute
|
43 |
+
delete
|
44 |
+
No virus
|
45 |
+
51 kB
|
46 |
{
|
47 |
"added_tokens_decoder": {
|
48 |
"128000": {
|
|
|
2097 |
"bos_token": "<|begin_of_text|>",
|
2098 |
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2099 |
"clean_up_tokenization_spaces": true,
|
2100 |
+
"eos_token": "<|eot_id|>",
|
2101 |
"model_input_names": [
|
2102 |
"input_ids",
|
2103 |
"attention_mask"
|
|
|
2107 |
"padding_side": "left",
|
2108 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2109 |
}
|
2110 |
+
|