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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": ".",
+  "architectures": [
+    "AlbertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "vocab_size": 50000
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9a7d58a444b5d8b256a2dc9923e9d2ce3918adf389a6b8ee8ba7669bfd2030
+size 57576476

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a389462d93417e10b45106189b32997b583d41b4e2421136f359404b9fe689ad
+size 83391338

special_tokens_map.json

@@ -0,0 +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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29a45ffb757d0acb1216f70e134c89c194e586ff42d026deb0c018b28d8daa7b
+size 1242045

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d6d8819f57daa41e8c0e73e6fa97471d8a4746f2d2337c7dc16c259d38f72bf
+size 83696976

tokenizer_config.json

@@ -0,0 +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"}