Upload version gender_classifier_multi_xlmroberta_base

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+tags:
+- text-classification
+- modernbert
+- generated-data
+base_model: xlm-roberta-base
+metrics:
+- name: loss
+  type: loss
+  value: 0.3350488543510437
+- name: accuracy
+  type: accuracy
+  value: 0.9124166666666667
+- name: f1
+  type: f1
+  value: 0.9120147312529937
+- name: precision
+  type: precision
+  value: 0.9128995023586967
+- name: recall
+  type: recall
+  value: 0.9124720693071042
+- name: runtime
+  type: runtime
+  value: 6.9012
+- name: samples_per_second
+  type: samples_per_second
+  value: 1738.831
+- name: steps_per_second
+  type: steps_per_second
+  value: 54.338
+- name: epoch
+  type: epoch
+  value: 3.0
+---
+
+# Gender Classifier (Fine-tuned xlm-roberta-base)
+
+This model was fine-tuned to classify text into: male, female, neutral
+
+## Performance Metrics
+| Metric | Value |
+| :--- | :--- |
+| **loss** | 0.3350 |
+| **accuracy** | 0.9124 |
+| **f1** | 0.9120 |
+| **precision** | 0.9129 |
+| **recall** | 0.9125 |
+| **runtime** | 6.9012 |
+| **samples_per_second** | 1738.8310 |
+| **steps_per_second** | 54.3380 |
+| **epoch** | 3.0000 |
+
+## Hyperparameters
+- **Batch Size**: 32
+- **Learning Rate**: 5e-05
+- **Epochs**: 3
+- **Weight Decay**: 0.01
+- **Mixed Precision (FP16)**: True
+
+## Quick Usage
+```python
+from transformers import pipeline
+
+# Load the model directly from this folder or HF Hub
+classifier = pipeline('text-classification', model='.')
+print(classifier('She is a great engineer.'))
+```

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "male",
+    "1": "female",
+    "2": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "female": 1,
+    "male": 0,
+    "neutral": 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",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7299b6f81fe17beec7ce54c2af975ac00880d2f27ac46426b6938f6f2679af17
+size 1112208084

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8a58b4a32779512659e3dd48ca133293443790856eab26e23661f65c39a833
+size 5905