Updated model

config.json

@@ -1,28 +1,87 @@
 {
-  "_name_or_path": "bert-base-uncased",
   "architectures": [
     "QuantizedBertForSequenceClassification"
   ],
+  "attention_key": {
+    "mode": "ema"
+  },
+  "attention_output": {
+    "mode": "ema",
+    "requantize_output": false
+  },
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "finetuning_task": "cola",
-  "gradient_checkpointing": false,
+  "attention_query": {
+    "mode": "ema"
+  },
+  "attention_value": {
+    "mode": "ema",
+    "requantize_output": false
+  },
+  "bos_token_id": 0,
+  "do_sample": false,
+  "eos_token_ids": 0,
+  "ffn_intermediate": {
+    "mode": "ema",
+    "requantize_output": false
+  },
+  "ffn_output": {
+    "mode": "ema",
+    "requantize_output": false
+  },
+  "finetuning_task": null,
+  "head": {
+    "mode": "ema",
+    "requantize_output": false,
+    "start_step": 200
+  },
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
   "layer_norm_eps": 1e-12,
+  "length_penalty": 1.0,
+  "max_length": 20,
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 12,
+  "num_beams": 1,
   "num_hidden_layers": 12,
+  "num_labels": 2,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_past": true,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
-  "torch_dtype": "float32",
-  "transformers_version": "4.12.5",
+  "pooler": {
+    "mode": "ema",
+    "requantize_output": false
+  },
+  "position_embeddings": {
+    "mode": "ema"
+  },
+  "pruned_heads": {},
+  "repetition_penalty": 1.0,
+  "temperature": 1.0,
+  "token_type_embeddings": {
+    "mode": "none"
+  },
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
   "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "use_bfloat16": false,
+  "vocab_size": 30522,
+  "word_embeddings": {
+    "mode": "ema"
+  }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3384be928331ccffbc5eeb5ebdac69d039d9332fc032b24b4fed542161e55184
-size 438723541
+oid sha256:10008e2fb48f29e9880e55273e47516e41e75548b8ff6ef8ba40602b0118ca99
+size 110019389

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
+{"do_lower_case": true, "max_len": 512}