Commit
•
121c1be
1
Parent(s):
b0966d6
Upload tokenizer
Browse files- tokenizer.json +17 -2
- tokenizer_config.json +2 -3
tokenizer.json
CHANGED
|
@@ -1,7 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
@@ -293,6 +307,7 @@
|
|
| 293 |
"continuing_subword_prefix": null,
|
| 294 |
"end_of_word_suffix": null,
|
| 295 |
"fuse_unk": false,
|
|
|
|
| 296 |
"vocab": {
|
| 297 |
"<|endoftext|>": 0,
|
| 298 |
"<|padding|>": 1,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 300,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 300
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 50280,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "[PAD]"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 307 |
"continuing_subword_prefix": null,
|
| 308 |
"end_of_word_suffix": null,
|
| 309 |
"fuse_unk": false,
|
| 310 |
+
"byte_fallback": false,
|
| 311 |
"vocab": {
|
| 312 |
"<|endoftext|>": 0,
|
| 313 |
"<|padding|>": 1,
|
tokenizer_config.json
CHANGED
|
@@ -1,10 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"bos_token": "<|endoftext|>",
|
|
|
|
| 4 |
"eos_token": "<|endoftext|>",
|
| 5 |
-
"model_max_length":
|
| 6 |
-
"name_or_path": "EleutherAI/pythia-410m",
|
| 7 |
-
"special_tokens_map_file": "/admin/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/4e49eadb5d14bd22f314ec3f45b69a87b88c7691/special_tokens_map.json",
|
| 8 |
"tokenizer_class": "GPTNeoXTokenizer",
|
| 9 |
"unk_token": "<|endoftext|>"
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 300,
|
|
|
|
|
|
|
| 7 |
"tokenizer_class": "GPTNeoXTokenizer",
|
| 8 |
"unk_token": "<|endoftext|>"
|
| 9 |
}
|