3v324v23 commited on
Commit
819c65a
1 Parent(s): 44f1603

fix embedding & logits order, add tokenizer

Browse files
optimizer_state.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec0e733cb1d91216216b32ebb16994b25b5afe8b46aa4a1561bf40f32d1b23e4
3
  size 608100493
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09b71dd97be34f00629a88bd82cc48df3496d7a5118085f34bce681cf4a2dc4
3
  size 608100493
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:722c180333b83162236a522c14bea9daf6e98abbbb827e64d395151c16a49bbe
3
  size 304042184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f7a6d0e8ad7ab7223176b7f86ae6ebfdc6b47d819a881cdfc1fa5a58b831518
3
  size 304042184
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "cls_token": "[CLS]", "pad_token": "<pad>", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "neuropark/sahajBERT", "tokenizer_class": "AlbertBengaliTokenizer"}