Upload XLMRobertaForSequenceClassification

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "ckpts/xlm-v-base-trimmed-de-5000-tweet-sentiment-de/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,
+  "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": 5002,
+  "vocabtrimmer": {
+    "mining_config": {
+      "dataset": "vocabtrimmer/mc4_validation",
+      "dataset_column": "text",
+      "dataset_name": "de",
+      "dataset_split": "validation",
+      "language": "de",
+      "min_frequency": 2,
+      "target_vocab_size": 5000
+    },
+    "stats": {
+      "compression_rate_embedding": 0.5547736374939138,
+      "compression_rate_full": 11.533308581100371,
+      "parameter_size_embedding/raw": 692451072,
+      "parameter_size_embedding/trimmed": 3841536,
+      "parameter_size_full/raw": 779396349,
+      "parameter_size_full/trimmed": 89890186,
+      "vocab_size/raw": 901629,
+      "vocab_size/trimmed": 5002
+    }
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ae08b736107da84454ae3ca8c46ecc2b9f00bd121e0ee745a0f765c85a0f0f
+size 359615469