Upload processor
Browse files- README.md +2 -2
- chat_template.json +1 -1
- special_tokens_map.json +3 -7
- tokenizer.json +2 -2
- tokenizer_config.json +6 -2
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
language:
|
3 |
- en
|
4 |
library_name: transformers
|
@@ -7,8 +9,6 @@ pipeline_tag: image-text-to-text
|
|
7 |
tags:
|
8 |
- multimodal
|
9 |
- aria
|
10 |
-
base_model:
|
11 |
-
- rhymes-ai/Aria-Base-64K
|
12 |
---
|
13 |
<!-- <p align="center">
|
14 |
<br>Aria</br>
|
|
|
1 |
---
|
2 |
+
base_model:
|
3 |
+
- rhymes-ai/Aria-Base-64K
|
4 |
language:
|
5 |
- en
|
6 |
library_name: transformers
|
|
|
9 |
tags:
|
10 |
- multimodal
|
11 |
- aria
|
|
|
|
|
12 |
---
|
13 |
<!-- <p align="center">
|
14 |
<br>Aria</br>
|
chat_template.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
{
|
2 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
3 |
-
}
|
|
|
1 |
{
|
2 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
3 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,12 +1,8 @@
|
|
1 |
{
|
|
|
|
|
2 |
"image_token": "<|img|>",
|
3 |
-
"pad_token":
|
4 |
-
"content": "<pad>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
"unk_token": {
|
11 |
"content": "<unk>",
|
12 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"image_prefix": "<fim_prefix>",
|
3 |
+
"image_suffix": "<fim_suffix>",
|
4 |
"image_token": "<|img|>",
|
5 |
+
"pad_token": "<pad>",
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"unk_token": {
|
7 |
"content": "<unk>",
|
8 |
"lstrip": false,
|
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 sha256:3b9b8ec511cd5849462cfc019fe913dd7e3da7fa8b72ffd92fc8b328906de687
|
3 |
+
size 11091479
|
tokenizer_config.json
CHANGED
@@ -321,7 +321,7 @@
|
|
321 |
"normalized": false,
|
322 |
"rstrip": false,
|
323 |
"single_word": false,
|
324 |
-
"special":
|
325 |
},
|
326 |
"40": {
|
327 |
"content": "<fim_middle>",
|
@@ -337,7 +337,7 @@
|
|
337 |
"normalized": false,
|
338 |
"rstrip": false,
|
339 |
"single_word": false,
|
340 |
-
"special":
|
341 |
},
|
342 |
"42": {
|
343 |
"content": "<fim_pad>",
|
@@ -4945,9 +4945,13 @@
|
|
4945 |
"clean_up_tokenization_spaces": false,
|
4946 |
"eos_token": null,
|
4947 |
"extra_special_tokens": {
|
|
|
|
|
4948 |
"image_token": "<|img|>",
|
4949 |
"pad_token": "<pad>"
|
4950 |
},
|
|
|
|
|
4951 |
"image_token": "<|img|>",
|
4952 |
"legacy": true,
|
4953 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
321 |
"normalized": false,
|
322 |
"rstrip": false,
|
323 |
"single_word": false,
|
324 |
+
"special": true
|
325 |
},
|
326 |
"40": {
|
327 |
"content": "<fim_middle>",
|
|
|
337 |
"normalized": false,
|
338 |
"rstrip": false,
|
339 |
"single_word": false,
|
340 |
+
"special": true
|
341 |
},
|
342 |
"42": {
|
343 |
"content": "<fim_pad>",
|
|
|
4945 |
"clean_up_tokenization_spaces": false,
|
4946 |
"eos_token": null,
|
4947 |
"extra_special_tokens": {
|
4948 |
+
"image_prefix": "<fim_prefix>",
|
4949 |
+
"image_suffix": "<fim_suffix>",
|
4950 |
"image_token": "<|img|>",
|
4951 |
"pad_token": "<pad>"
|
4952 |
},
|
4953 |
+
"image_prefix": "<fim_prefix>",
|
4954 |
+
"image_suffix": "<fim_suffix>",
|
4955 |
"image_token": "<|img|>",
|
4956 |
"legacy": true,
|
4957 |
"model_max_length": 1000000000000000019884624838656,
|