initial model upload

.gitattributes

@@ -33,3 +33,5 @@ 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
+model.safetensors filter=lfs diff=lfs merge=lfs -text

artifact.metadata

@@ -0,0 +1,50 @@
+{
+    "query_token_id": "[QueryMarker]",
+    "doc_token_id": "[DocumentMarker]",
+    "query_token": "[QueryMarker]",
+    "doc_token": "[DocumentMarker]",
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "load_index_with_mmap": false,
+    "index_path": null,
+    "nbits": 2,
+    "kmeans_niters": 20,
+    "resume": false,
+    "similarity": "cosine",
+    "bsize": 32,
+    "accumsteps": 1,
+    "lr": null,
+    "maxsteps": null,
+    "save_every": null,
+    "warmup": null,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 7,
+    "use_ib_negatives": false,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": true,
+    "model_name": null,
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": true,
+    "interaction": "colbert",
+    "doc_maxlen": 300,
+    "mask_punctuation": true,
+    "checkpoint": null,
+    "triples": null,
+    "collection": null,
+    "queries": null,
+    "index_name": null,
+    "overwrite": false,
+    "root": "",
+    "experiment": "default",
+    "index_root": null,
+    "name": "2024-08/15/14.12.19",
+    "rank": 0,
+    "nranks": 1,
+    "amp": false,
+    "gpus": 2,
+    "avoid_fork_if_possible": false,
+    "dim": 128
+}

config.json

@@ -0,0 +1,45 @@
+{
+    "_name_or_path": "jinaai/jina-embeddings-v3-xlm-large-pairs-vol5",
+    "architectures": [
+        "HF_ColBERT"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "auto_map": {
+        "AutoConfig": "jinaai/xlm-roberta-flash-implementation--configuration_xlm_roberta.XLMRobertaFlashConfig",
+        "AutoModel": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaModel",
+        "AutoModelForMaskedLM": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaForMaskedLM",
+        "AutoModelForPreTraining": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaForPreTraining"
+    },
+    "bos_token_id": 0,
+    "classifier_dropout": null,
+    "emb_pooler": null,
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
+    "load_trained_adapters": false,
+    "lora_adaptations": null,
+    "lora_alpha": 1,
+    "lora_dropout_p": 0.0,
+    "lora_main_params_trainable": false,
+    "lora_prompts": null,
+    "lora_rank": 4,
+    "matryoshka_dimensions": null,
+    "max_position_embeddings": 8194,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "output_past": true,
+    "pad_token_id": 1,
+    "position_embedding_type": "rotary",
+    "rotary_emb_base": 10000.0,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.43.2",
+    "truncate_dim": null,
+    "type_vocab_size": 1,
+    "use_cache": true,
+    "use_flash_attn": true,
+    "vocab_size": 250004
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741387d37db6027ada13c4705b8bb32719a09dc71873f54814d1182cd8943806
+size 1119027888

special_tokens_map.json

@@ -0,0 +1,67 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[QueryMarker]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[DocumentMarker]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60aeacc24f3d75c34628dfee5b7fed4bcce9a55def52b49f62a0b09d65a44b0b
+size 17083370

tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "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
+    },
+    "250002": {
+      "content": "[QueryMarker]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250003": {
+      "content": "[DocumentMarker]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[QueryMarker]",
+    "[DocumentMarker]"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 8194,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}