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 +1,46 @@
+{
+  "_name_or_path": "multilingual-e5-small-4096",
+  "adaptive": true,
+  "architectures": [
+    "LSGBertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoConfig": "modeling_lsg_bert.LSGBertConfig",
+    "AutoModel": "modeling_lsg_bert.LSGBertModel",
+    "AutoModelForCausalLM": "modeling_lsg_bert.LSGBertLMHeadModel",
+    "AutoModelForMaskedLM": "modeling_lsg_bert.LSGBertForMaskedLM",
+    "AutoModelForMultipleChoice": "modeling_lsg_bert.LSGBertForMultipleChoice",
+    "AutoModelForPreTraining": "modeling_lsg_bert.LSGBertForPreTraining",
+    "AutoModelForQuestionAnswering": "modeling_lsg_bert.LSGBertForQuestionAnswering",
+    "AutoModelForSequenceClassification": "modeling_lsg_bert.LSGBertForSequenceClassification",
+    "AutoModelForTokenClassification": "modeling_lsg_bert.LSGBertForTokenClassification"
+  },
+  "base_model_prefix": "lsg",
+  "block_size": 128,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "lsh_num_pre_rounds": 1,
+  "mask_first_token": false,
+  "max_position_embeddings": 4096,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_global_tokens": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pool_with_global": true,
+  "position_embedding_type": "absolute",
+  "sparse_block_size": 128,
+  "sparsity_factor": 2,
+  "sparsity_type": "norm",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f7357dc3fcc487a046adc7bc02b697435a405aa4648f1011612486f1145e1e
+size 475802235

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd5b4819c3296733b52bfc33ec56306b57109cf63cdf030eafc9377176fbd8d
+size 119713117

quantize_config.json

@@ -0,0 +1,30 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Pow",
+                "Cast",
+                "ReduceMean",
+                "Sub",
+                "Div",
+                "Slice",
+                "Sqrt",
+                "Constant",
+                "MatMul",
+                "Concat",
+                "Erf",
+                "Unsqueeze",
+                "Softmax",
+                "Add",
+                "Transpose",
+                "Shape",
+                "Mul",
+                "Gather",
+                "Reshape"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b44a9d7b51c3c62626640cda0e2c2f70fdacdc25bbbd68038369d14ebdf4c39
+size 17082730

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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
+  },
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}