Upload 7 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

artifact.metadata

@@ -0,0 +1,73 @@
+{
+    "nprobe": 2,
+    "ncandidates": 8192,
+    "index_path": null,
+    "nbits": 1,
+    "kmeans_niters": 20,
+    "num_partitions_max": 10000000,
+    "similarity": "l2",
+    "bsize": 32,
+    "accumsteps": 1,
+    "lr": 3e-6,
+    "maxsteps": 500000,
+    "save_every": null,
+    "resume": false,
+    "resume_optimizer": false,
+    "warmup": null,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": false,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "shuffle_every_epoch": false,
+    "save_steps": 50000,
+    "save_epochs": -1,
+    "epochs": 1,
+    "input_arguments": {},
+    "model_type": "xlm-roberta-base",
+    "init_from_lm": null,
+    "local_models_repository": null,
+    "ranks_fn": null,
+    "topK": 100,
+    "student_teacher_temperature": 1.0,
+    "student_teacher_top_loss_weight": 0.5,
+    "teacher_model_type": "xlm-roberta-base",
+    "teacher_doc_maxlen": 180,
+    "distill_query_passage_separately": false,
+    "query_only": false,
+    "loss_function": null,
+    "query_weight": 0.5,
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 220,
+    "mask_punctuation": true,
+    "checkpoint": "\/home\/adityas\/adi\/output\/test_training\/none\/2024-03\/27\/11.57.55\/checkpoints\/colbert-LAST.dnn",
+    "teacher_checkpoint": "\/home\/adityas\/adi\/output\/test_training_teacher\/none\/2024-03\/25\/13.01.32\/checkpoints\/colbert-LAST.dnn",
+    "triples": "\/home\/adityas\/adi\/data\/triples.train.tiny.tsv",
+    "teacher_triples": "\/home\/adityas\/adi\/data\/triples.train.tiny.tsv",
+    "collection": null,
+    "queries": null,
+    "index_name": null,
+    "overwrite": false,
+    "root": "\/home\/adityas\/adi\/output",
+    "experiment": "test_training",
+    "index_root": null,
+    "name": "2024-03\/28\/14.47.16",
+    "rank": 0,
+    "nranks": 1,
+    "amp": true,
+    "gpus": 1,
+    "meta": {
+        "hostname": "ccde7f558d02",
+        "git_branch": null,
+        "git_hash": null,
+        "git_commit_datetime": null,
+        "current_datetime": "Mar 29, 2024 ;  9:06AM IST (+0530)",
+        "cmd": "\/home\/adityas\/.local\/lib\/python3.8\/site-packages\/ipykernel_launcher.py -f \/home\/adityas\/.local\/share\/jupyter\/runtime\/kernel-6a8cc166-77aa-4390-adfb-ae3411baa584.json",
+        "version": "colbert-v0.4"
+    }
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "HF_ColBERT_XLMR"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1204ece62a7c1914836a467afeccf574b2b793c96e9765af8a8280289f7c7339
+size 1112591992

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
+size 17082756

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "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": "</s>",
+      "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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}