Zeb commited on
Commit ·
fde09f8
1
Parent(s): ce169aa
Rename frequency tokenizers
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- frequency_128000/merges.txt +0 -0
- frequency_128000/merges_data.csv +0 -0
- frequency_128000/tokenizer.json +0 -0
- frequency_128000/vocab.json +0 -0
- frequency_16000/merges.txt +0 -0
- frequency_16000/merges_data.csv +0 -0
- frequency_16000/tokenizer.json +0 -0
- frequency_16000/vocab.json +0 -0
- frequency_256000/merges.txt +0 -0
- frequency_256000/merges_data.csv +0 -0
- frequency_256000/tokenizer.json +2 -2
- frequency_256000/vocab.json +0 -0
- frequency_32000/merges.txt +0 -0
- frequency_32000/merges_data.csv +0 -0
- frequency_32000/tokenizer.json +0 -0
- frequency_32000/vocab.json +0 -0
- frequency_64000/merges.txt +0 -0
- frequency_64000/merges_data.csv +0 -0
- frequency_64000/tokenizer.json +0 -0
- frequency_64000/vocab.json +0 -0
- frequency_8064/merges.txt +0 -0
- frequency_8064/merges_data.csv +0 -0
- frequency_8064/tokenizer.json +0 -0
- frequency_8064/vocab.json +0 -0
- fw57M_Entropy_frequency_128000/merges.txt +0 -0
- fw57M_Entropy_frequency_128000/merges_data.csv +0 -0
- fw57M_Entropy_frequency_128000/special_tokens_map.json +0 -4
- fw57M_Entropy_frequency_128000/tokenizer.json +0 -0
- fw57M_Entropy_frequency_128000/tokenizer_config.json +0 -29
- fw57M_Entropy_frequency_128000/vocab.json +0 -0
- fw57M_Entropy_frequency_16000/merges.txt +0 -0
- fw57M_Entropy_frequency_16000/merges_data.csv +0 -0
- fw57M_Entropy_frequency_16000/special_tokens_map.json +0 -4
- fw57M_Entropy_frequency_16000/tokenizer.json +0 -0
- fw57M_Entropy_frequency_16000/tokenizer_config.json +0 -29
- fw57M_Entropy_frequency_16000/vocab.json +0 -0
- fw57M_Entropy_frequency_256000/merges.txt +0 -0
- fw57M_Entropy_frequency_256000/merges_data.csv +0 -0
- fw57M_Entropy_frequency_256000/special_tokens_map.json +0 -4
- fw57M_Entropy_frequency_256000/tokenizer.json +0 -3
- fw57M_Entropy_frequency_256000/tokenizer_config.json +0 -29
- fw57M_Entropy_frequency_256000/vocab.json +0 -0
- fw57M_Entropy_frequency_32000/merges.txt +0 -0
- fw57M_Entropy_frequency_32000/merges_data.csv +0 -0
- fw57M_Entropy_frequency_32000/special_tokens_map.json +0 -4
- fw57M_Entropy_frequency_32000/tokenizer.json +0 -0
- fw57M_Entropy_frequency_32000/tokenizer_config.json +0 -29
- fw57M_Entropy_frequency_32000/vocab.json +0 -0
- fw57M_Entropy_frequency_64000/merges.txt +0 -0
- fw57M_Entropy_frequency_64000/merges_data.csv +0 -0
frequency_128000/merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_128000/merges_data.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_128000/tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_128000/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_16000/merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_16000/merges_data.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_16000/tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_16000/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_256000/merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_256000/merges_data.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_256000/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 sha256:47a19d76ccd8400f78de8cb1bb0cc81e948596a5a9337c90d739c81a7c59ce8b
|
| 3 |
+
size 19623518
|
frequency_256000/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_32000/merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_32000/merges_data.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_32000/tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_32000/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_64000/merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_64000/merges_data.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_64000/tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_64000/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_8064/merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_8064/merges_data.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_8064/tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequency_8064/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_128000/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_128000/merges_data.csv
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_128000/special_tokens_map.json
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"eos_token": "<|endoftext|>",
|
| 3 |
-
"pad_token": "<|padding|>"
|
| 4 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_frequency_128000/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_128000/tokenizer_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": true,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"0": {
|
| 5 |
-
"content": "<|padding|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"1": {
|
| 13 |
-
"content": "<|endoftext|>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
}
|
| 20 |
-
},
|
| 21 |
-
"bos_token": null,
|
| 22 |
-
"clean_up_tokenization_spaces": false,
|
| 23 |
-
"eos_token": "<|endoftext|>",
|
| 24 |
-
"extra_special_tokens": {},
|
| 25 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 26 |
-
"pad_token": "<|padding|>",
|
| 27 |
-
"tokenizer_class": "PreTrainedTokenizer",
|
| 28 |
-
"unk_token": null
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_frequency_128000/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_16000/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_16000/merges_data.csv
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_16000/special_tokens_map.json
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"eos_token": "<|endoftext|>",
|
| 3 |
-
"pad_token": "<|padding|>"
|
| 4 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_frequency_16000/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_16000/tokenizer_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": true,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"0": {
|
| 5 |
-
"content": "<|padding|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"1": {
|
| 13 |
-
"content": "<|endoftext|>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
}
|
| 20 |
-
},
|
| 21 |
-
"bos_token": null,
|
| 22 |
-
"clean_up_tokenization_spaces": false,
|
| 23 |
-
"eos_token": "<|endoftext|>",
|
| 24 |
-
"extra_special_tokens": {},
|
| 25 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 26 |
-
"pad_token": "<|padding|>",
|
| 27 |
-
"tokenizer_class": "PreTrainedTokenizer",
|
| 28 |
-
"unk_token": null
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_frequency_16000/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_256000/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_256000/merges_data.csv
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_256000/special_tokens_map.json
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"eos_token": "<|endoftext|>",
|
| 3 |
-
"pad_token": "<|padding|>"
|
| 4 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_frequency_256000/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:47a19d76ccd8400f78de8cb1bb0cc81e948596a5a9337c90d739c81a7c59ce8b
|
| 3 |
-
size 19623518
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_frequency_256000/tokenizer_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": true,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"0": {
|
| 5 |
-
"content": "<|padding|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"1": {
|
| 13 |
-
"content": "<|endoftext|>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
}
|
| 20 |
-
},
|
| 21 |
-
"bos_token": null,
|
| 22 |
-
"clean_up_tokenization_spaces": false,
|
| 23 |
-
"eos_token": "<|endoftext|>",
|
| 24 |
-
"extra_special_tokens": {},
|
| 25 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 26 |
-
"pad_token": "<|padding|>",
|
| 27 |
-
"tokenizer_class": "PreTrainedTokenizer",
|
| 28 |
-
"unk_token": null
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_frequency_256000/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_32000/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_32000/merges_data.csv
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_32000/special_tokens_map.json
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"eos_token": "<|endoftext|>",
|
| 3 |
-
"pad_token": "<|padding|>"
|
| 4 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_frequency_32000/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_32000/tokenizer_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": true,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"0": {
|
| 5 |
-
"content": "<|padding|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"1": {
|
| 13 |
-
"content": "<|endoftext|>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
}
|
| 20 |
-
},
|
| 21 |
-
"bos_token": null,
|
| 22 |
-
"clean_up_tokenization_spaces": false,
|
| 23 |
-
"eos_token": "<|endoftext|>",
|
| 24 |
-
"extra_special_tokens": {},
|
| 25 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 26 |
-
"pad_token": "<|padding|>",
|
| 27 |
-
"tokenizer_class": "PreTrainedTokenizer",
|
| 28 |
-
"unk_token": null
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_frequency_32000/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_64000/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_frequency_64000/merges_data.csv
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|