Upload XLMRobertaForSequenceClassification

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "ckpts/xlm-roberta-base-trimmed-en-tweet-sentiment-en/best_model",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 173237,
+  "vocabtrimmer": {
+    "mining_config": {
+      "dataset": "vocabtrimmer/mc4_validation",
+      "dataset_column": "text",
+      "dataset_name": "en",
+      "dataset_split": "validation",
+      "language": "en",
+      "min_frequency": 2,
+      "target_vocab_size": null
+    },
+    "stats": {
+      "compression_rate_embedding": 69.29424564603484,
+      "compression_rate_full": 78.78788855514016,
+      "parameter_size_embedding/raw": 192001536,
+      "parameter_size_embedding/trimmed": 133046016,
+      "parameter_size_full/raw": 278295186,
+      "parameter_size_full/trimmed": 219262901,
+      "vocab_size/raw": 250002,
+      "vocab_size/trimmed": 173237
+    }
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aed926b16ec367e37040aece40caee773638b56d791b612127227fd6052e283
+size 876435125