Upload 10 files

quantization of models

config.json

@@ -1,5 +1,6 @@
 {
-  "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "Mozilla/content-multilabel-iab-classifier",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -63,7 +64,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "multi_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.49.0",
   "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 sha256:3c3c076e3f4924ee497e0f7fb34f85857ba955e092d3254816eee0cac86feebd
+size 133740267

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c79fc1ced771200eab9a96005a0d88dbfa491055265dd9ff892247f1b29e30
+size 67021343

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae0f888d3e323d5180ca12bb7959cec55fe525a45623b5c5158155133a7b3d0
+size 62087374

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8c08f4544840e7e02a44af9c82d342528c6756b1cf3a95c94c9703fe275490
+size 34125553

quantize_config.json

@@ -0,0 +1,14 @@
+{
+    "modes": [
+        "q4",
+        "q8",
+        "fp16"
+    ],
+    "per_channel": true,
+    "reduce_range": true,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1,
+    "op_block_list": null
+}

tokenizer_config.json

@@ -45,6 +45,7 @@
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "max_length": 256,
   "model_max_length": 1000000000000000019884624838656,