admin/LLM-from-scratch
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update tokenizer weights

Browse Source
This commit is contained in:
coffee
2025-05-07 11:25:19 +08:00
parent c5ab40c2df
commit f594d5dbf2
14 changed files with 310662 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
weights_tokenizer/dolly_tokenizer_spm/expand_tokenizer.model
Executable
BIN
View File
Binary file not shown.
weights_tokenizer/dolly_tokenizer_spm/tokenizer.model
Executable
BIN
View File
Binary file not shown.
weights_tokenizer/dolly_tokenizer_spm/tokenizer_en.model
Executable
BIN
View File
Binary file not shown.
weights_tokenizer/dolly_tokenizer_spm/tokenizer_en.vocab
Executable
+1000
View File
File diff suppressed because it is too large Load Diff
weights_tokenizer/dolly_tokenizer_spm/tokenizer_zh.model
Executable
BIN
View File
Binary file not shown.
weights_tokenizer/dolly_tokenizer_spm/tokenizer_zh.vocab
Executable
+32000
View File
File diff suppressed because it is too large Load Diff
weights_tokenizer/hf_tokenizer/special_tokens_map.json
Executable
+7
View File
@@ -0,0 +1,7 @@
{
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"unk_token": "[UNK]"
}
weights_tokenizer/hf_tokenizer/tokenizer.json
Executable
+75528
View File
File diff suppressed because it is too large Load Diff
weights_tokenizer/hf_tokenizer/tokenizer_config.json
Executable
+53
View File
@@ -0,0 +1,53 @@
{
"added_tokens_decoder": {
"0": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": false,
"cls_token": "[CLS]",
"extra_special_tokens": {},
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "[UNK]"
}
weights_tokenizer/hf_tokenizer_BBPE/.ipynb_checkpoints/tokenizer-checkpoint.json
Executable
+63243
View File
File diff suppressed because it is too large Load Diff
weights_tokenizer/hf_tokenizer_BBPE/special_tokens_map.json
Executable
+7
View File
@@ -0,0 +1,7 @@
{
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"unk_token": "[UNK]"
}
weights_tokenizer/hf_tokenizer_BBPE/tokenizer.json
Executable
+63243
View File
File diff suppressed because it is too large Load Diff
weights_tokenizer/hf_tokenizer_BBPE/tokenizer_config.json
Executable
+53
View File
@@ -0,0 +1,53 @@
{
"added_tokens_decoder": {
"0": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": false,
"cls_token": "[CLS]",
"extra_special_tokens": {},
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "[UNK]"
}
weights_tokenizer/tokenizer.json
Executable
+75528
View File
File diff suppressed because it is too large Load Diff