initial commit

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "BertLMHeadModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "encoder_ln_mode": "post-ln",
+  "fused_linear_layer": true,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "apex",
+  "layernorm_embedding": false,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "sparse_mask_prediction": true,
+  "transformers_version": "4.4.0",
+  "type_vocab_size": 2,
+  "useLN": true,
+  "use_cache": true,
+  "vocab_size": 50000
+}

deepspeed_config.json

@@ -0,0 +1,14 @@
+{
+  "fp16": {
+    "enabled": true,
+    "hysteresis": 2,
+    "loss_scale": 0,
+    "loss_scale_window": 1000,
+    "min_loss_scale": 1
+  },
+  "gradient_clipping": 0.0,
+  "steps_per_print": 100,
+  "train_batch_size": 4096,
+  "train_micro_batch_size_per_gpu": 128,
+  "wall_clock_breakdown": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7cdd26bae6ade815f558a1fba1743e4aadbf717c2fc84e27ab95a65edfa6916
+size 250249001

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": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "dumitrescustefan/bert-base-romanian-cased-v1"}