Upload XLMRobertaForSequenceClassification

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/dimos/storage_mnt/tweetTopic-multi/xlmr_base_final/final_model/best_model_all",
+  "_name_or_path": "/home/dimos/storage_mnt/tweetTopic-multi/xlmr_large_final/final_model/best_model_all",
   "architectures": [
     "XLMRobertaForSequenceClassification"
   ],
@@ -7,10 +7,9 @@
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "arts_&_culture",
     "1": "business_&_entrepreneurs",
@@ -33,7 +32,7 @@
     "18": "youth_&_student_life"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "arts_&_culture": 0,
     "business_&_entrepreneurs": 1,
@@ -58,8 +57,8 @@
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "xlm-roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49277bcb0fcf77a81e38c2c01e47ab9332470c4a2e24def28d36bc6fec11e993
-size 1112257300
+oid sha256:03391a9ae49e8b8b6bec1fb48ee008ad60c29e6258781f4240b4884ac588d0b1
+size 2239688372