Upload folder using huggingface_hub
Browse files
bpe128k_dclm-edu150M/raw_tok_name.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
bpe320000_2025-09-20T17-01-07
|
bpe128k_dclm-edu150M/special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "<|eos|>"
|
| 3 |
+
}
|
bpe128k_dclm-edu150M/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
bpe128k_dclm-edu150M/tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
}
|