Instructions to use bitadin/medium-title-latest with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bitadin/medium-title-latest with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("bitadin/medium-title-latest") model = AutoModelForSeq2SeqLM.from_pretrained("bitadin/medium-title-latest", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload tokenizer
Browse files- special_tokens_map.json +21 -3
- tokenizer.json +20 -4
special_tokens_map.json
CHANGED
|
@@ -101,7 +101,25 @@
|
|
| 101 |
"<extra_id_98>",
|
| 102 |
"<extra_id_99>"
|
| 103 |
],
|
| 104 |
-
"eos_token":
|
| 105 |
-
|
| 106 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 107 |
}
|
|
|
|
| 101 |
"<extra_id_98>",
|
| 102 |
"<extra_id_99>"
|
| 103 |
],
|
| 104 |
+
"eos_token": {
|
| 105 |
+
"content": "</s>",
|
| 106 |
+
"lstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"rstrip": false,
|
| 109 |
+
"single_word": false
|
| 110 |
+
},
|
| 111 |
+
"pad_token": {
|
| 112 |
+
"content": "<pad>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false
|
| 117 |
+
},
|
| 118 |
+
"unk_token": {
|
| 119 |
+
"content": "<unk>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
}
|
| 125 |
}
|
tokenizer.json
CHANGED
|
@@ -1,7 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
@@ -950,7 +964,8 @@
|
|
| 950 |
"pre_tokenizer": {
|
| 951 |
"type": "Metaspace",
|
| 952 |
"replacement": "▁",
|
| 953 |
-
"add_prefix_space": true
|
|
|
|
| 954 |
},
|
| 955 |
"post_processor": {
|
| 956 |
"type": "TemplateProcessing",
|
|
@@ -1009,7 +1024,8 @@
|
|
| 1009 |
"decoder": {
|
| 1010 |
"type": "Metaspace",
|
| 1011 |
"replacement": "▁",
|
| 1012 |
-
"add_prefix_space": true
|
|
|
|
| 1013 |
},
|
| 1014 |
"model": {
|
| 1015 |
"type": "Unigram",
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 89,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 89
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 0,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "<pad>"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 964 |
"pre_tokenizer": {
|
| 965 |
"type": "Metaspace",
|
| 966 |
"replacement": "▁",
|
| 967 |
+
"add_prefix_space": true,
|
| 968 |
+
"prepend_scheme": "always"
|
| 969 |
},
|
| 970 |
"post_processor": {
|
| 971 |
"type": "TemplateProcessing",
|
|
|
|
| 1024 |
"decoder": {
|
| 1025 |
"type": "Metaspace",
|
| 1026 |
"replacement": "▁",
|
| 1027 |
+
"add_prefix_space": true,
|
| 1028 |
+
"prepend_scheme": "always"
|
| 1029 |
},
|
| 1030 |
"model": {
|
| 1031 |
"type": "Unigram",
|