Upload 10 files

onnx converted model for finetuned distilbert NER

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "dslim/distilbert-NER",
+  "_name_or_path": "Mozilla/distilbert-NER-LoRA",
   "activation": "gelu",
   "architectures": [
     "DistilBertForTokenClassification"
@@ -41,7 +41,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.43.4",
   "vocab_size": 28996
 }

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626fe45d2038e3894b781599696af0376a2431346b492f71bbd351bac41ebe8c
+size 260940064

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b6ca590bf7f28e82adc87df888fe1811a0022043de48ea92432508333d9ee1
+size 130544330

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04e01cb093d6a8afba3b6d40c52943ce7c0082fdba87b6d00104d9e7a062a2d7
+size 117594921

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9219cbe3e4c3bd072b22464dfeb57cf3dc1b583e5d61d5282d64cf49d9922db8
+size 65788336

quantize_config.json

@@ -0,0 +1,11 @@
+{
+    "modes": [
+        "q4"
+    ],
+    "per_channel": true,
+    "reduce_range": true,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1
+}