Upload 6 files
Browse files- added_tokens.json +4 -0
- chat_template.json +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -7
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<image>": 32001,
|
3 |
+
"<video>": 32000
|
4 |
+
}
|
chat_template.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chat_template": "{% for message in messages %}{% if message['role'] != 'system' %}{{ message['role'].upper() + ': '}}{% endif %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>\n' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] + ' '}}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] + ' '}}{% endgeneration %}{% endfor %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}"
|
3 |
+
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
-
"add_prefix_space":
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
@@ -28,7 +28,7 @@
|
|
28 |
"special": true
|
29 |
},
|
30 |
"32000": {
|
31 |
-
"content": "<
|
32 |
"lstrip": false,
|
33 |
"normalized": false,
|
34 |
"rstrip": false,
|
@@ -36,7 +36,7 @@
|
|
36 |
"special": true
|
37 |
},
|
38 |
"32001": {
|
39 |
-
"content": "<
|
40 |
"lstrip": false,
|
41 |
"normalized": false,
|
42 |
"rstrip": false,
|
@@ -47,11 +47,20 @@
|
|
47 |
"bos_token": "<s>",
|
48 |
"clean_up_tokenization_spaces": false,
|
49 |
"eos_token": "</s>",
|
50 |
-
"
|
51 |
-
|
|
|
|
|
|
|
|
|
|
|
52 |
"pad_token": "<unk>",
|
53 |
-
"
|
|
|
|
|
|
|
54 |
"tokenizer_class": "LlamaTokenizer",
|
55 |
"unk_token": "<unk>",
|
56 |
-
"use_default_system_prompt":
|
|
|
57 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
|
|
28 |
"special": true
|
29 |
},
|
30 |
"32000": {
|
31 |
+
"content": "<video>",
|
32 |
"lstrip": false,
|
33 |
"normalized": false,
|
34 |
"rstrip": false,
|
|
|
36 |
"special": true
|
37 |
},
|
38 |
"32001": {
|
39 |
+
"content": "<image>",
|
40 |
"lstrip": false,
|
41 |
"normalized": false,
|
42 |
"rstrip": false,
|
|
|
47 |
"bos_token": "<s>",
|
48 |
"clean_up_tokenization_spaces": false,
|
49 |
"eos_token": "</s>",
|
50 |
+
"extra_special_tokens": {
|
51 |
+
"image_token": "<image>",
|
52 |
+
"video_token": "<video>"
|
53 |
+
},
|
54 |
+
"image_token": "<image>",
|
55 |
+
"legacy": false,
|
56 |
+
"model_max_length": 4096,
|
57 |
"pad_token": "<unk>",
|
58 |
+
"padding_side": "left",
|
59 |
+
"processor_class": "LlavaNextVideoProcessor",
|
60 |
+
"sp_model_kwargs": {},
|
61 |
+
"spaces_between_special_tokens": false,
|
62 |
"tokenizer_class": "LlamaTokenizer",
|
63 |
"unk_token": "<unk>",
|
64 |
+
"use_default_system_prompt": false,
|
65 |
+
"video_token": "<video>"
|
66 |
}
|