Added language: guj_Gujr

guj_Gujr-nllb1.3b-moses/colbert-50000/artifact.metadata

@@ -0,0 +1,57 @@
+{
+    "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,
+    "similarity": "cosine",
+    "bsize": 128,
+    "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": "bert-base-multilingual-uncased",
+    "triples": "data\/\/triples.train.tsv",
+    "collection": "..\/data_nllb_1.3B_quantized_8bit\/256\/guj_Gujr\/\/collection.tsv",
+    "queries": "..\/data_nllb_1.3B_quantized_8bit\/256\/guj_Gujr\/query.train.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": "\/saif\/saif_ir\/indicIRsuite\/ColBERT\/experiments",
+    "experiment": "mmarco_moses_nllb_1.3B",
+    "index_root": null,
+    "name": "2023-10\/05\/02.45.26",
+    "rank": 0,
+    "nranks": 1,
+    "amp": true,
+    "gpus": 1,
+    "meta": {
+        "hostname": "ddbf18d969d5",
+        "git_branch": "main",
+        "git_hash": "43ae55077c5c793d382b7ee3ed6b57630bbcd22e",
+        "git_commit_datetime": "2023-04-19 17:21:22-07:00",
+        "current_datetime": "Oct 05, 2023 ; 12:03PM UTC (+0000)",
+        "cmd": "train_multilingual-final.py guj_Gujr nllb_1.3B",
+        "version": "colbert-v0.4"
+    }
+}

guj_Gujr-nllb1.3b-moses/colbert-50000/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bert-base-multilingual-uncased",
+  "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": "4.28.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105879
+}

guj_Gujr-nllb1.3b-moses/colbert-50000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41f988bddf342acccecec26a93d25d5a7cff72a362c09105b0c01cf2f57a31d
+size 669891377

guj_Gujr-nllb1.3b-moses/colbert-50000/special_tokens_map.json

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

guj_Gujr-nllb1.3b-moses/colbert-50000/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "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]"
+}