Initial commit

README.md

@@ -0,0 +1,11 @@
+---
+language: en
+tags: fill-mask
+datasets: 
+- wikipedia
+- bookcorpus
+---
+# 80% 1x4 Block Sparse BERT-Large (uncased) Prune OFA
+This model is was created using Prune OFA method described in [Prune Once for All: Sparse Pre-Trained Language Models](https://arxiv.org/abs/2111.05754) presented in ENLSP NeurIPS Workshop 2021.
+
+For further details on the model and its result, see our paper and our implementation available [here](https://github.com/IntelLabs/Model-Compression-Research-Package/tree/main/research/prune-once-for-all).

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/store/nosnap/results/mlm/wikipedia_bookcorpus/bert-large/baseline-new",
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "keys_to_ignore_at_inference": [
+    "prediction_logits"
+  ],
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:280259693aabbd422a25a70c209b6401a36df750277645271b82c9616824473d
+size 1345074168

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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-large-uncased"}