Upload DistilBertForSequenceClassification

config.json

@@ -1,28 +1,25 @@
 {
-  "_name_or_path": "/project/mousavi_lab/msba24/team1/roberta-large_doubled_sample",
+  "_name_or_path": "/project/mousavi_lab/msba24/team1/2distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.40.0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:113683613e09a568abc3fc552beb27af53d6d495adb02de508191258f56d62fa
-size 1421495416
+oid sha256:3617e21716ca1ceb09df3d6efa0fb941d9e5562a80dd786f18dd4773cf16d21d
+size 267832560