Upload tokenizer
Browse files- README.md +2 -2
- tokenizer.json +2 -2
- tokenizer_config.json +1 -0
README.md
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
language:
|
3 |
- en
|
4 |
- ko
|
5 |
-
|
6 |
tags:
|
7 |
- facebook
|
8 |
- meta
|
@@ -10,7 +10,7 @@ tags:
|
|
10 |
- llama
|
11 |
- llama-3
|
12 |
- llama-3-ko
|
13 |
-
|
14 |
license_name: llama3
|
15 |
license_link: LICENSE
|
16 |
---
|
|
|
2 |
language:
|
3 |
- en
|
4 |
- ko
|
5 |
+
license: other
|
6 |
tags:
|
7 |
- facebook
|
8 |
- meta
|
|
|
10 |
- llama
|
11 |
- llama-3
|
12 |
- llama-3-ko
|
13 |
+
pipeline_tag: text-generation
|
14 |
license_name: llama3
|
15 |
license_link: LICENSE
|
16 |
---
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e134af98b985517b4f068e3755ae90d4e9cd2d45d328325dc503f1c6b2d06cc7
|
3 |
+
size 9085698
|
tokenizer_config.json
CHANGED
@@ -2050,6 +2050,7 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
"eos_token": "<|end_of_text|>",
|
2055 |
"model_input_names": [
|
|
|
2050 |
}
|
2051 |
},
|
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": "<|end_of_text|>",
|
2056 |
"model_input_names": [
|