Zeb
commited on
Commit
·
6b0beee
1
Parent(s):
2e4b4eb
Fix tokenizers
Browse files- .gitattributes +1 -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
- fw57M_Entropy_thresholdBX_8064/stats.csv → frequencymulti_256000/merges.txt +0 -0
- fw57M_Entropy_thresholdBX_32000/stats.csv → frequencymulti_256000/merges_data.csv +0 -0
- frequencymulti_256000/special_tokens_map.json +4 -0
- frequencymulti_256000/tokenizer.json +3 -0
- {fw57M_Entropy_thresholdBX_32000 → frequencymulti_256000}/tokenizer_config.json +2 -10
- fw57M_Entropy_thresholdBX_16000/stats.csv → frequencymulti_256000/vocab.json +0 -0
- fw57M_Entropy_thresholdBX_16000/special_tokens_map.json +0 -6
- fw57M_Entropy_thresholdBX_16000/tokenizer.json +0 -0
- fw57M_Entropy_thresholdBX_16000/tokenizer_config.json +0 -37
- fw57M_Entropy_thresholdBX_16000/vocab.json +0 -0
- fw57M_Entropy_thresholdBX_32000/special_tokens_map.json +0 -6
- fw57M_Entropy_thresholdBX_32000/tokenizer.json +0 -0
- fw57M_Entropy_thresholdBX_32000/vocab.json +0 -0
- fw57M_Entropy_thresholdBX_8064/special_tokens_map.json +0 -6
- fw57M_Entropy_thresholdBX_8064/tokenizer.json +0 -0
- fw57M_Entropy_thresholdBX_8064/tokenizer_config.json +0 -37
- fw57M_Entropy_thresholdBX_8064/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -54,3 +54,4 @@ mutual-information_256000/special_tokens_map.json filter=lfs diff=lfs merge=lfs
|
|
| 54 |
mutual-information_256000/tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
|
| 55 |
mutual-information_256000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 56 |
fw57M_Entropy_threshold_128000/stats.csv filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 54 |
mutual-information_256000/tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
|
| 55 |
mutual-information_256000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 56 |
fw57M_Entropy_threshold_128000/stats.csv filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
frequencymulti_256000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
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
|
|
|
fw57M_Entropy_thresholdBX_8064/stats.csv → frequencymulti_256000/merges.txt
RENAMED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_thresholdBX_32000/stats.csv → frequencymulti_256000/merges_data.csv
RENAMED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frequencymulti_256000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "<|endoftext|>",
|
| 3 |
+
"pad_token": "<|padding|>"
|
| 4 |
+
}
|
frequencymulti_256000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed37c183a6fdf658a259f23b64ca57aab65a1b96dbcb8343b06e108fe6fbec55
|
| 3 |
+
size 20274248
|
{fw57M_Entropy_thresholdBX_32000 → frequencymulti_256000}/tokenizer_config.json
RENAMED
|
@@ -16,22 +16,14 @@
|
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
| 19 |
-
},
|
| 20 |
-
"259": {
|
| 21 |
-
"content": "<|unk|>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
}
|
| 28 |
},
|
| 29 |
-
"bos_token":
|
| 30 |
"clean_up_tokenization_spaces": false,
|
| 31 |
"eos_token": "<|endoftext|>",
|
| 32 |
"extra_special_tokens": {},
|
| 33 |
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
"pad_token": "<|padding|>",
|
| 35 |
"tokenizer_class": "PreTrainedTokenizer",
|
| 36 |
-
"unk_token":
|
| 37 |
}
|
|
|
|
| 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_thresholdBX_16000/stats.csv → frequencymulti_256000/vocab.json
RENAMED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_thresholdBX_16000/special_tokens_map.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<|endoftext|>",
|
| 3 |
-
"eos_token": "<|endoftext|>",
|
| 4 |
-
"pad_token": "<|padding|>",
|
| 5 |
-
"unk_token": "<|unk|>"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_thresholdBX_16000/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_thresholdBX_16000/tokenizer_config.json
DELETED
|
@@ -1,37 +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 |
-
"259": {
|
| 21 |
-
"content": "<|unk|>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
-
}
|
| 28 |
-
},
|
| 29 |
-
"bos_token": "<|endoftext|>",
|
| 30 |
-
"clean_up_tokenization_spaces": false,
|
| 31 |
-
"eos_token": "<|endoftext|>",
|
| 32 |
-
"extra_special_tokens": {},
|
| 33 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
-
"pad_token": "<|padding|>",
|
| 35 |
-
"tokenizer_class": "PreTrainedTokenizer",
|
| 36 |
-
"unk_token": "<|unk|>"
|
| 37 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_thresholdBX_16000/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_thresholdBX_32000/special_tokens_map.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<|endoftext|>",
|
| 3 |
-
"eos_token": "<|endoftext|>",
|
| 4 |
-
"pad_token": "<|padding|>",
|
| 5 |
-
"unk_token": "<|unk|>"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_thresholdBX_32000/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_thresholdBX_32000/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_thresholdBX_8064/special_tokens_map.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<|endoftext|>",
|
| 3 |
-
"eos_token": "<|endoftext|>",
|
| 4 |
-
"pad_token": "<|padding|>",
|
| 5 |
-
"unk_token": "<|unk|>"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_thresholdBX_8064/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
fw57M_Entropy_thresholdBX_8064/tokenizer_config.json
DELETED
|
@@ -1,37 +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 |
-
"259": {
|
| 21 |
-
"content": "<|unk|>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
-
}
|
| 28 |
-
},
|
| 29 |
-
"bos_token": "<|endoftext|>",
|
| 30 |
-
"clean_up_tokenization_spaces": false,
|
| 31 |
-
"eos_token": "<|endoftext|>",
|
| 32 |
-
"extra_special_tokens": {},
|
| 33 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
-
"pad_token": "<|padding|>",
|
| 35 |
-
"tokenizer_class": "PreTrainedTokenizer",
|
| 36 |
-
"unk_token": "<|unk|>"
|
| 37 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fw57M_Entropy_thresholdBX_8064/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|