BiGS 1000k

Bidirectional Gated State Space Model. 346M parameters, 23 layers, max sentence length 128, train 1000k steps with 97,280 tokens per step

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BiGSForMaskedLM"
+  ],
+  "classifier_dropout": null,
+  "decode": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 128,
+  "model_type": "BiGS",
+  "num_hidden_layers": 23,
+  "num_ssm": 64,
+  "pad_token_id": 0,
+  "pooler_type": "mean",
+  "position_embedding_type": "absolute",
+  "pre_norm": true,
+  "transformers_version": "4.26.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be760c0d3987a0591609854429729bc8de07304d40f36b7873bc2317afb42192
+size 1385274778

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 128, "model_max_length": 128, "special_tokens_map_file": null, "name_or_path": "bigs-uncased", "tokenizer_class": "BiGSTokenizer"}