Upload folder using huggingface_hub

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/GW/carpet/nobackup/czhang/msmarcopsg/.capreolus/results/collection-msmarcopsg/benchmark-msmarcopsg/collection-msmarcopsg/benchmark-msmarcopsg/collection-msmarcopsg/benchmark-msmarcopsg/searcher-msptop200_firststage-tct/task-rank_filter-False/collection-msmarcopsg/benchmark-msmarcopsg/collection-msmarcopsg/index-anserini_indexstops-True_stemmer-None/tokenizer-berttokenizer_pretrained-bert-base-uncased/extractor-LCEbertpassage_maxqlen-50_maxseqlen-256_numpassages-1_passagelen-150_prob-0.1_seed-42_sentences-False_stride-100/collection-msmarcopsg/benchmark-msmarcopsg/trainer-tensorflow_amp-True_batch-16_bertlr-1e-05_decay-0.1_decayiters-10_decaytype-linear_eager-False_evalbatch-256_itersize-48000_loss-lce_lr-1e-05_niters-10_seed-42_validatefreq-10_warmupiters-1/reranker-TFBERTMaxP_aggregation-max_hidden_dropout_prob-0.1_pretrained-google/electra-base-discriminator/sampler-LCE_nneg-31_seed-42/task-rerank_fold-s1_metrics-default_optimize-MRR@10_seed-42_testthreshold-1000_threshold-1000/hgf-format/",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.9.1",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d634f12b125d3a58363fbe541c68d63e434cb1936fd6edcef4a1cda6e972ea2
+size 438022857

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}