Upload folder using huggingface_hub

artifact.metadata

@@ -0,0 +1,63 @@
+{
+    "query_token_id": "[unused0]",
+    "doc_token_id": "[unused1]",
+    "query_token": "[Q]",
+    "doc_token": "[D]",
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "load_index_with_mmap": false,
+    "index_path": null,
+    "index_bsize": 64,
+    "nbits": 1,
+    "kmeans_niters": 4,
+    "resume": false,
+    "pool_factor": 1,
+    "clustering_mode": "hierarchical",
+    "protected_tokens": 0,
+    "similarity": "cosine",
+    "bsize": 24,
+    "accumsteps": 1,
+    "lr": 3e-6,
+    "maxsteps": 500000,
+    "save_every": null,
+    "warmup": null,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": false,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": null,
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 220,
+    "mask_punctuation": true,
+    "checkpoint": "hunkim\/sentence-transformer-klue",
+    "triples": "triples",
+    "collection": "collection.tsv",
+    "queries": "query.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": "\/data\/ephemeral\/home\/github\/ljm\/experiments",
+    "experiment": "training",
+    "index_root": null,
+    "name": "2024-10\/16\/05.29.48",
+    "rank": 0,
+    "nranks": 1,
+    "amp": true,
+    "gpus": 1,
+    "avoid_fork_if_possible": false,
+    "meta": {
+        "hostname": "instance-12254",
+        "git_branch": "ljm",
+        "git_hash": "a9843af1d98492b948bcdea32b1dd6dfb4fc983e",
+        "git_commit_datetime": "2024-10-16 05:01:49+00:00",
+        "current_datetime": "Oct 16, 2024 ;  5:38AM UTC (+0000)",
+        "cmd": "\/data\/ephemeral\/home\/miniconda3\/envs\/colbert\/lib\/python3.8\/site-packages\/ipykernel_launcher.py --f=\/data\/ephemeral\/home\/.local\/share\/jupyter\/runtime\/kernel-v38336916ae49b63aaecf770e9930cfd964b3ef851.json",
+        "version": "colbert-v0.4"
+    }
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "hunkim/sentence-transformer-klue",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:612860700e9cd16ecc32cb488ed1ac5deea41cc46fc8a096cae41f5d31ed8a65
+size 442889720

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}