Upload folder using huggingface_hub

config.json

@@ -1,10 +1,12 @@
 {
+  "_attn_implementation_autoset": true,
   "_name_or_path": "BAAI/bge-base-en-v1.5",
   "architectures": [
     "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "export_model_type": "transformer",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -24,29 +26,33 @@
     "auto_cast": null,
     "auto_cast_type": null,
     "compiler_type": "neuronx-cc",
-    "compiler_version": "2.11.0.34+c5231f848",
-    "disable_fallback": false,
-    "disable_fast_relayout": false,
+    "compiler_version": "2.16.372.0+4a9b2326",
     "dynamic_batch_size": false,
+    "inline_weights_to_neff": false,
     "input_names": [
       "input_ids",
-      "attention_mask",
-      "token_type_ids"
+      "attention_mask"
     ],
+    "model_type": "transformer",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
     "output_names": [
-      "last_hidden_state",
-      "pooler_output"
+      "token_embeddings",
+      "sentence_embedding"
     ],
     "static_batch_size": 1,
-    "static_sequence_length": 384
+    "static_sequence_length": 384,
+    "tensor_parallel_size": 1
   },
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "task": null,
+  "task": "feature-extraction",
   "torch_dtype": "float32",
-  "transformers_version": "4.35.0",
+  "torchscript": true,
+  "transformers_version": "4.48.3",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a8b0cd957cab25a3dc4e69a4f09588e482b2c5eb60a59cef18f718c5d71c72b
-size 273801602
+oid sha256:c32bd2adef487a1a9b55995610f41144419cf1fe2e391c3b1cd3eeb7f5af9e18
+size 436483448

tokenizer_config.json

@@ -45,6 +45,7 @@
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "never_split": null,