Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "e5-base-multilingual-4096",
+  "adaptive": true,
+  "architectures": [
+    "LSGXLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoConfig": "modeling_lsg_xlm_roberta.LSGXLMRobertaConfig",
+    "AutoModel": "modeling_lsg_xlm_roberta.LSGXLMRobertaModel",
+    "AutoModelForCausalLM": "modeling_lsg_xlm_roberta.LSGXLMRobertaForCausalLM",
+    "AutoModelForMaskedLM": "modeling_lsg_xlm_roberta.LSGXLMRobertaForMaskedLM",
+    "AutoModelForMultipleChoice": "modeling_lsg_xlm_roberta.LSGXLMRobertaForMultipleChoice",
+    "AutoModelForQuestionAnswering": "modeling_lsg_xlm_roberta.LSGXLMRobertaForQuestionAnswering",
+    "AutoModelForSequenceClassification": "modeling_lsg_xlm_roberta.LSGXLMRobertaForSequenceClassification",
+    "AutoModelForTokenClassification": "modeling_lsg_xlm_roberta.LSGXLMRobertaForTokenClassification"
+  },
+  "base_model_prefix": "lsg",
+  "block_size": 128,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "lsh_num_pre_rounds": 1,
+  "mask_first_token": false,
+  "max_position_embeddings": 4098,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_global_tokens": 1,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "pool_with_global": true,
+  "position_embedding_type": "absolute",
+  "sparse_block_size": 128,
+  "sparsity_factor": 2,
+  "sparsity_type": "norm",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a10f5984c11953045d2ef2ebcfe00125320952d82b2318e00f62f35e2a17d2c
+size 1121097810

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bca905967a647de5182bf9b275913bdd6acd52c4fb2c0d2db090572dd8d169
+size 281428852

quantize_config.json

@@ -0,0 +1,36 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Div",
+                "Concat",
+                "Reshape",
+                "MatMul",
+                "Constant",
+                "Not",
+                "Sqrt",
+                "ReduceMean",
+                "Sub",
+                "Slice",
+                "Erf",
+                "CumSum",
+                "Shape",
+                "Expand",
+                "ConstantOfShape",
+                "Equal",
+                "Transpose",
+                "Unsqueeze",
+                "Pow",
+                "Gather",
+                "Add",
+                "Mul",
+                "Cast",
+                "Softmax",
+                "Where"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46afe88da5fd71bdbab5cfab5e84c1adce59c246ea5f9341bbecef061891d0a7
+size 17082913

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}