Delete bpe128k_dclm-edu150k
Browse files
bpe128k_dclm-edu150k/raw_tok_name.txt
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
bpe320000_2025-09-20T17-01-07
|
|
|
|
|
|
bpe128k_dclm-edu150k/special_tokens_map.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"eos_token": "<|eos|>"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
bpe128k_dclm-edu150k/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
bpe128k_dclm-edu150k/tokenizer_config.json
DELETED
|
@@ -1,17 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "<|eos|>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
}
|
| 11 |
-
},
|
| 12 |
-
"clean_up_tokenization_spaces": true,
|
| 13 |
-
"eos_token": "<|eos|>",
|
| 14 |
-
"extra_special_tokens": {},
|
| 15 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 16 |
-
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 17 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|