Upload folder using huggingface_hub

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "almanach/camembert-base",
+  "architectures": [
+    "CamembertForMaskedLM"
+  ],
+  "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_hidden_states": true,
+  "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
+}

config_sparse_retrievers.json

@@ -0,0 +1,20 @@
+{
+    "model_name_or_path": "almanach/camembert-base",
+    "similarity": "cos_sim",
+    "padding": "longest",
+    "truncation": true,
+    "max_query_length": 32,
+    "max_doc_length": 128,
+    "add_special_tokens": true,
+    "augment_query_to_maxlen": false,
+    "augment_doc_to_maxlen": false,
+    "query_prefix": null,
+    "doc_prefix": null,
+    "pooling": "max",
+    "pruning_topk": null,
+    "pruning_threshold": null,
+    "__version__": {
+        "pytorch": "2.1.2+cu121",
+        "transformers": "4.36.2"
+    }
+}

mmarco_smalldev_scores.csv

@@ -0,0 +1,2 @@
+epoch,steps,cos_sim-Accuracy@1,cos_sim-Precision@5,cos_sim-Recall@5,cos_sim-Precision@10,cos_sim-Recall@10,cos_sim-Precision@20,cos_sim-Recall@20,cos_sim-Precision@50,cos_sim-Recall@50,cos_sim-Precision@100,cos_sim-Recall@100,cos_sim-Precision@200,cos_sim-Recall@200,cos_sim-Precision@500,cos_sim-Recall@500,cos_sim-Precision@1000,cos_sim-Recall@1000,cos_sim-MRR@10,cos_sim-MRR@100,cos_sim-NDCG@10,cos_sim-NDCG@100,cos_sim-MAP@10,cos_sim-MAP@100
+0,100000,0.15515759312320918,0.07610315186246419,0.36473256924546327,0.04858166189111748,0.4632521489971347,0.029255014326647562,0.5557784145176695,0.014020057306590257,0.6632999044890162,0.007825214899713466,0.7393505253104108,0.004217048710601718,0.7958452722063037,0.001824641833810889,0.8596227316141355,0.000954441260744986,0.8986270296084049,0.24682317960613007,0.25788603566583085,0.2958119380996196,0.35399215859320554,0.24154337411500734,0.25296812696912013

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:134e046752df70ab6b05021eab6e8469bc5a8de7b0a1ed11df3c3b7d509557ae
+size 442646188

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 +1,84 @@
+{
+  "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>",
+  "device": "cuda",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}