Upload folder using huggingface_hub

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "gte-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",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614c8f2040db61a30cabcd6ba65d9a4592b3d14f1f73db4266397fdbaaa286db
+size 138627192

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f42da8c9b55a9f5c3612777cf675af1a7455a5b4063a91ad1b84f6aec474b00
+size 35419358

quantize_config.json

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

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 4096,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}