Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,5 @@ multilingual-e5-base/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 snowflake-arctic-embed-m-v2.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3-embedding-0.6b/model.onnx.data filter=lfs diff=lfs merge=lfs -text
 qwen3-embedding-0.6b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+arctic-embed-m-v2.0/model.onnx.data filter=lfs diff=lfs merge=lfs -text
+arctic-embed-m-v2.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text

arctic-embed-m-v2.0/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 768,
+    "pooling_mode_cls_token": true,
+    "pooling_mode_mean_tokens": false,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": false,
+    "include_prompt": true
+}

arctic-embed-m-v2.0/config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "GteModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_hf_alibaba_nlp_gte.GteConfig",
+    "AutoModel": "modeling_hf_alibaba_nlp_gte.GteModel"
+  },
+  "classifier_dropout": 0.1,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "matryoshka_dimensions": [
+    256
+  ],
+  "max_position_embeddings": 8192,
+  "model_type": "gte",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pack_qkv": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "rope",
+  "rope_scaling": null,
+  "rope_theta": 160000,
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 1,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 250048
+}

arctic-embed-m-v2.0/config_sentence_transformers.json

@@ -0,0 +1,11 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.7.0.dev0",
+    "transformers": "4.39.3",
+    "pytorch": "2.1.0+cu121"
+  },
+  "prompts": {
+    "query": "query: "
+  },
+  "default_prompt_name": null
+}

arctic-embed-m-v2.0/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1ea2341193d02dcb2452edadfa2b32bf6cced2b34cf8dc0b664e1ca8232b96
+size 2111319

arctic-embed-m-v2.0/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e502378d93ea574242f86a0e4723535098e5f6b702c3eaeb72047458095a06
+size 1225785344

arctic-embed-m-v2.0/modules.json

@@ -0,0 +1,20 @@
+[
+    {
+      "idx": 0,
+      "name": "0",
+      "path": "",
+      "type": "sentence_transformers.models.Transformer"
+    },
+    {
+      "idx": 1,
+      "name": "1",
+      "path": "1_Pooling",
+      "type": "sentence_transformers.models.Pooling"
+    },
+    {
+      "idx": 2,
+      "name": "2",
+      "path": "2_Normalize",
+      "type": "sentence_transformers.models.Normalize"
+    }
+  ]

arctic-embed-m-v2.0/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "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
+  }
+}

arctic-embed-m-v2.0/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc5c1151948923156f20bcafd54fd796705d693f8d7b56c83aec49d651f6d602
+size 17082986

arctic-embed-m-v2.0/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 32768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}