Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>NOTUSED": 32005
+}

artifact.metadata

@@ -0,0 +1,58 @@
+{
+    "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,
+    "nbits": 1,
+    "kmeans_niters": 4,
+    "resume": false,
+    "similarity": "cosine",
+    "bsize": 64,
+    "accumsteps": 1,
+    "lr": 3e-6,
+    "maxsteps": 200000,
+    "save_every": null,
+    "warmup": null,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": true,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": true,
+    "model_name": "camembert-base",
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": true,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 256,
+    "mask_punctuation": true,
+    "checkpoint": "camembert-base",
+    "triples": "data\/mmarco\/triples.train.ids.small.jsonl",
+    "collection": "data\/mmarco\/french_collection.tsv",
+    "queries": "data\/mmarco\/french_queries.train.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": "output\/training",
+    "experiment": "mmarco",
+    "index_root": null,
+    "name": "2023-12\/21\/15.44.53",
+    "rank": 0,
+    "nranks": 1,
+    "amp": true,
+    "gpus": 1,
+    "meta": {
+        "hostname": "jupyterlab-gpu-2-4-jgfkq",
+        "git_branch": "main",
+        "git_hash": "49363ffb7f6ca212ff2780edb86b485d0379e836",
+        "git_commit_datetime": "2023-12-21 19:32:07+01:00",
+        "current_datetime": "Dec 22, 2023 ; 12:53PM CET (+0100)",
+        "cmd": "src\/training\/colbertv1.py --dataset mmarco --language french --nway 2 --model_name camembert-base --dim 128 --similarity cosine --doc_maxlen 256 --query_maxlen 32 --mask_punctuation --attend_to_mask_tokens --maxsteps 200000 --lr 3e-6 --bsize 64 --accumsteps 1 --use_ib_negatives --ignore_scores --distillation_alpha 1.0 --nbits 1 --kmeans_niters 4 --data_dir data --output_dir output\/training",
+        "version": "colbert-v0.4"
+    }
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "camembert-base",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "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": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054acd780709dd9647983ad3ce71490d9ab9e15905cb495c97f39a28ad548f96
+size 442905080

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
+size 810912

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
+  ],
+  "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_config.json

@@ -0,0 +1,83 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "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>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<unk>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
+  ],
+  "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": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}