Upload model with adaptive-classifier

README.md

@@ -0,0 +1,110 @@
+---
+language: multilingual
+tags:
+- adaptive-classifier
+- text-classification
+- continuous-learning
+license: apache-2.0
+---
+
+# Adaptive Classifier
+
+This model is an instance of an [adaptive-classifier](https://github.com/codelion/adaptive-classifier) that allows for continuous learning and dynamic class addition.
+
+You can install it with `pip install adaptive-classifier`.
+
+## Model Details
+
+- Base Model: Goader/modern-liberta-large
+- Number of Classes: 39
+- Total Examples: 2904
+- Embedding Dimension: 1024
+
+## Class Distribution
+
+```
+0: 474 examples (16.3%)
+1: 2 examples (0.1%)
+2: 56 examples (1.9%)
+3: 1 examples (0.0%)
+4: 79 examples (2.7%)
+5: 26 examples (0.9%)
+6: 53 examples (1.8%)
+7: 59 examples (2.0%)
+8: 82 examples (2.8%)
+9: 18 examples (0.6%)
+10: 33 examples (1.1%)
+11: 34 examples (1.2%)
+12: 107 examples (3.7%)
+13: 123 examples (4.2%)
+14: 400 examples (13.8%)
+15: 124 examples (4.3%)
+16: 63 examples (2.2%)
+17: 24 examples (0.8%)
+18: 1 examples (0.0%)
+19: 142 examples (4.9%)
+20: 150 examples (5.2%)
+21: 4 examples (0.1%)
+22: 7 examples (0.2%)
+23: 62 examples (2.1%)
+24: 36 examples (1.2%)
+25: 27 examples (0.9%)
+26: 80 examples (2.8%)
+27: 89 examples (3.1%)
+28: 4 examples (0.1%)
+29: 15 examples (0.5%)
+30: 117 examples (4.0%)
+31: 48 examples (1.7%)
+32: 7 examples (0.2%)
+33: 1 examples (0.0%)
+34: 237 examples (8.2%)
+35: 2 examples (0.1%)
+36: 9 examples (0.3%)
+37: 10 examples (0.3%)
+38: 98 examples (3.4%)
+```
+
+## Usage
+
+```python
+from adaptive_classifier import AdaptiveClassifier
+
+# Load the model
+classifier = AdaptiveClassifier.from_pretrained("adaptive-classifier/model-name")
+
+# Make predictions
+text = "Your text here"
+predictions = classifier.predict(text)
+print(predictions)  # List of (label, confidence) tuples
+
+# Add new examples
+texts = ["Example 1", "Example 2"]
+labels = ["class1", "class2"]
+classifier.add_examples(texts, labels)
+```
+
+## Training Details
+
+- Training Steps: 1
+- Examples per Class: See distribution above
+- Prototype Memory: Active
+- Neural Adaptation: Active
+
+## Limitations
+
+This model:
+- Requires at least 3 examples per class
+- Has a maximum of 1000 examples per class
+- Updates prototypes every 100 examples
+
+## Citation
+
+```bibtex
+@software{adaptive_classifier,
+  title = {Adaptive Classifier: Dynamic Text Classification with Continuous Learning},
+  author = {Sharma, Asankhaya},
+  year = {2025},
+  publisher = {GitHub},
+  url = {https://github.com/codelion/adaptive-classifier}
+}
+```

config.json

@@ -0,0 +1,159 @@
+{
+  "config": {
+    "batch_size": 32,
+    "cost_coefficients": {},
+    "cost_function_type": "separable",
+    "device_map": "auto",
+    "early_stopping_patience": 3,
+    "enable_strategic_mode": false,
+    "epochs": 10,
+    "ewc_lambda": 100.0,
+    "gradient_checkpointing": false,
+    "learning_rate": 0.001,
+    "max_examples_per_class": 1000,
+    "max_length": 512,
+    "min_confidence": 0.1,
+    "min_examples_per_class": 3,
+    "neural_weight": 0.3,
+    "num_representative_examples": 5,
+    "prototype_update_frequency": 100,
+    "prototype_weight": 0.7,
+    "quantization": null,
+    "similarity_threshold": 0.6,
+    "strategic_blend_regular_weight": 0.6,
+    "strategic_blend_strategic_weight": 0.4,
+    "strategic_lambda": 0.1,
+    "strategic_prediction_head_weight": 0.5,
+    "strategic_prediction_proto_weight": 0.5,
+    "strategic_robust_head_weight": 0.2,
+    "strategic_robust_proto_weight": 0.8,
+    "strategic_training_frequency": 10,
+    "warmup_steps": 0
+  },
+  "embedding_dim": 1024,
+  "id_to_label": {
+    "0": 0,
+    "1": 1,
+    "10": 10,
+    "11": 11,
+    "12": 12,
+    "13": 13,
+    "14": 14,
+    "15": 15,
+    "16": 16,
+    "17": 17,
+    "18": 18,
+    "19": 19,
+    "2": 2,
+    "20": 20,
+    "21": 21,
+    "22": 22,
+    "23": 23,
+    "24": 24,
+    "25": 25,
+    "26": 26,
+    "27": 27,
+    "28": 28,
+    "29": 29,
+    "3": 3,
+    "30": 30,
+    "31": 31,
+    "32": 32,
+    "33": 33,
+    "34": 34,
+    "35": 35,
+    "36": 36,
+    "37": 37,
+    "38": 38,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "7": 7,
+    "8": 8,
+    "9": 9
+  },
+  "label_to_id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "7": 7,
+    "8": 8,
+    "9": 9,
+    "10": 10,
+    "11": 11,
+    "12": 12,
+    "13": 13,
+    "14": 14,
+    "15": 15,
+    "16": 16,
+    "17": 17,
+    "18": 18,
+    "19": 19,
+    "20": 20,
+    "21": 21,
+    "22": 22,
+    "23": 23,
+    "24": 24,
+    "25": 25,
+    "26": 26,
+    "27": 27,
+    "28": 28,
+    "29": 29,
+    "30": 30,
+    "31": 31,
+    "32": 32,
+    "33": 33,
+    "34": 34,
+    "35": 35,
+    "36": 36,
+    "37": 37,
+    "38": 38
+  },
+  "model_name": "Goader/modern-liberta-large",
+  "train_steps": 1,
+  "training_history": {
+    "0": 474,
+    "1": 2,
+    "2": 56,
+    "3": 1,
+    "4": 79,
+    "5": 26,
+    "6": 53,
+    "7": 59,
+    "8": 82,
+    "9": 18,
+    "10": 33,
+    "11": 34,
+    "12": 107,
+    "13": 123,
+    "14": 400,
+    "15": 124,
+    "16": 63,
+    "17": 24,
+    "18": 1,
+    "19": 142,
+    "20": 150,
+    "21": 4,
+    "22": 7,
+    "23": 62,
+    "24": 36,
+    "25": 27,
+    "26": 80,
+    "27": 89,
+    "28": 4,
+    "29": 15,
+    "30": 117,
+    "31": 48,
+    "32": 7,
+    "33": 1,
+    "34": 237,
+    "35": 2,
+    "36": 9,
+    "37": 10,
+    "38": 98
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad88378b82b3355b340e600133838ecdacdb76315919694a79750f5048a0592
+size 6541012

onnx/config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "ModernBertForMaskedLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 2,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 1024,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 2624,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 3,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "vocab_size": 64000
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e714caa4a50be3bcb7d440c7d265d15c4b0cca728055eb587cd7bf12d78fd5f2
+size 1635488755

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5994c43e70dd9abcb3ec3583eb934a8e7fa8d33f00672256650f3c7cf4a9eb6f
+size 409885430

onnx/ort_config.json

@@ -0,0 +1,33 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QOperator",
+    "is_static": false,
+    "mode": "IntegerOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "Conv",
+      "MatMul",
+      "Attention",
+      "LSTM",
+      "Gather",
+      "Transpose",
+      "EmbedLayerNormalization"
+    ],
+    "per_channel": false,
+    "qdq_add_pair_to_weight": false,
+    "qdq_dedicated_pair": false,
+    "qdq_op_type_per_channel_support_to_axis": {
+      "MatMul": 1
+    },
+    "reduce_range": false,
+    "weights_dtype": "QInt8",
+    "weights_symmetric": true
+  },
+  "use_external_data_format": false
+}