ibraheemmoosa commited on
Commit
120256b
1 Parent(s): 6b6d0c1

xlmindic-base-uniscript tokenizer and model weights (in Pytorch, TF and Flax)

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": ".",
3
+ "architectures": [
4
+ "AlbertForPreTraining"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "embedding_size": 128,
10
+ "eos_token_id": 3,
11
+ "hidden_act": "gelu_new",
12
+ "hidden_dropout_prob": 0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 3072,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_groups": 1,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 0,
24
+ "position_embedding_type": "absolute",
25
+ "transformers_version": "4.15.0",
26
+ "type_vocab_size": 2,
27
+ "vocab_size": 50000
28
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9a7d58a444b5d8b256a2dc9923e9d2ce3918adf389a6b8ee8ba7669bfd2030
3
+ size 57576476
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a389462d93417e10b45106189b32997b583d41b4e2421136f359404b9fe689ad
3
+ size 83391338
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}}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a45ffb757d0acb1216f70e134c89c194e586ff42d026deb0c018b28d8daa7b
3
+ size 1242045
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d6d8819f57daa41e8c0e73e6fa97471d8a4746f2d2337c7dc16c259d38f72bf
3
+ size 83696976
tokenizer.vocab ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "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, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "tokenizer_class": "AlbertTokenizer"}