Upload folder using huggingface_hub

artifact.metadata

@@ -0,0 +1,67 @@
+{
+    "query_token_id": "[unused0]",
+    "doc_token_id": "[unused1]",
+    "query_token": "[Q]",
+    "doc_token": "[D]",
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "index_path": null,
+    "nbits": 1,
+    "kmeans_niters": 4,
+    "resume": false,
+    "seed": 12345,
+    "similarity": "cosine",
+    "bsize": 16,
+    "eval_bsize": 64,
+    "accumsteps": 8,
+    "lr": 3e-6,
+    "maxsteps": 500000,
+    "save_every": null,
+    "warmup": null,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 32,
+    "use_ib_negatives": true,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": "bert-base-uncased",
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 220,
+    "mask_punctuation": true,
+    "wandb_name": "QACG-SUM SR",
+    "wandb_project": "ColBERTv2",
+    "checkpoint": "bert-base-multilingual-cased",
+    "triples": "\/mnt\/data\/factcheck\/wiki\/sum_cs_en_pl_sk\/20230801\/colbertv2\/qacg\/triples\/trn_triples_nway128_evidence+anserini_balanced_shuf.jsonl",
+    "eval_triples": "\/mnt\/data\/factcheck\/wiki\/sum_cs_en_pl_sk\/20230801\/colbertv2\/qacg\/triples\/dev_triples_nway128_evidence+anserini_balanced_shuf.jsonl",
+    "max_eval_triples": 10000,
+    "batches_to_eval": 100,
+    "early_patience": 100,
+    "auto_score": false,
+    "collection": "\/mnt\/data\/factcheck\/wiki\/sum_cs_en_pl_sk\/20230801\/colbertv2\/qacg\/collection.jsonl",
+    "queries": "\/mnt\/data\/factcheck\/wiki\/sum_cs_en_pl_sk\/20230801\/colbertv2\/qacg\/queries\/train_qacg_queries_balanced_shuf.jsonl",
+    "eval_queries": "\/mnt\/data\/factcheck\/wiki\/sum_cs_en_pl_sk\/20230801\/colbertv2\/qacg\/queries\/dev_qacg_queries_balanced_shuf.jsonl",
+    "index_name": null,
+    "overwrite": false,
+    "root": "\/mnt\/data\/factcheck\/wiki\/sum_cs_en_pl_sk\/20230801\/colbertv2\/qacg\/experiments",
+    "experiment": "\/mnt\/data\/factcheck\/wiki\/sum_cs_en_pl_sk\/20230801\/colbertv2\/qacg\/checkpoints\/bert-base-multilingual-cased\/nway32_anserini_balanced_shuf_231029_200426",
+    "index_root": null,
+    "name": "2023-10\/29\/20.04.21",
+    "rank": 0,
+    "nranks": 1,
+    "amp": true,
+    "gpus": 1,
+    "meta": {
+        "hostname": "g05",
+        "git_branch": "main",
+        "git_hash": "03bd1f70a5fe550fe5f727a62138f75f8a805591",
+        "git_commit_datetime": "2023-02-26 12:10:34+03:00",
+        "current_datetime": "Oct 31, 2023 ;  8:52AM CET (+0100)",
+        "cmd": "scripts\/train.py cfg\/train\/wiki_sum_cs_en_pl_sk\/train_final.config.py",
+        "version": "colbert-v0.4"
+    }
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210522449e9201b0db0c75b60da2df2c33fd8756c06687f36e015ea14f5895a8
+size 711875053

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 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "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]"
+}