Upload Russian Constructicon span predictor model

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaForQuestionAnswering"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 35054
+}

eval_results.txt

@@ -0,0 +1,4 @@
+correct = 373
+eval_loss = -9.542310393258427
+incorrect = 198
+similar = 2271

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:302af33edd02ce86c66a29bacbd0e40c36f1b5f4905493ad6ae282fddf2d82ce
+size 1354992496

model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "correct", "early_stopping_metric_minimize": false, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 32, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 3e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": 42, "max_grad_norm": 1.0, "max_seq_length": 384, "model_name": "DeepPavlov/xlm-roberta-large-en-ru", "model_type": "xlmroberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 10, "optimizer": "AdamW", "output_dir": "qa_model", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 94, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": -1, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 32, "train_custom_parameters_only": false, "trust_remote_code": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 288, "weight_decay": 0.0, "model_class": "QuestionAnsweringModel", "doc_stride": 128, "lazy_loading": false, "max_answer_length": 100, "max_query_length": 64, "n_best_size": 5, "null_score_diff_threshold": 0.0, "special_tokens_list": []}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73badd66c0986425dca529605e2b9581f7c9b642dd011dde058e772830199f71
+size 2710216696

readme.md

@@ -0,0 +1,95 @@
+---
+tags:
+- transformers
+- question-answering
+- russian
+- constructicon
+- nlp
+- linguistics
+base_model: DeepPavlov/xlm-roberta-large-en-ru
+language:
+- ru
+pipeline_tag: question-answering
+widget:
+- text: "Что вам здесь нужно?"
+  context: "Что вам здесь нужно?"
+  example_title: "Question construction span"
+- text: "Петр так и замер на месте."
+  context: "Петр так и замер на месте."
+  example_title: "Adverbial construction span"
+---
+
+# Russian Constructicon Span Predictor
+
+A question-answering model for identifying construction spans in Russian text. Fine-tuned to locate specific Constructicon pattern implementations within text examples.
+
+## Model Details
+
+- **Base model:** [DeepPavlov/xlm-roberta-large-en-ru](https://huggingface.co/DeepPavlov/xlm-roberta-large-en-ru)
+- **Task:** Question Answering / Span Prediction
+- **Language:** Russian
+- **Training:** QA task where context=example, question=construction pattern, answer=construction span
+
+## Usage
+
+### Primary Usage (RusCxnPipe Library)
+
+This model is designed for use with the [RusCxnPipe](https://github.com/your-username/ruscxnpipe) library:
+
+```python
+from ruscxnpipe import SpanPredictor
+
+predictor = SpanPredictor(model_name="Futyn-Maker/ruscxn-span-predictor")
+
+examples_with_patterns = [
+    {
+        "example": "Что вам здесь нужно?",
+        "patterns": [{"id": "pattern1", "pattern": "что NP-Dat Cop нужно?"}]
+    }
+]
+
+results = predictor.predict_spans(examples_with_patterns)
+span_info = results[0]['patterns'][0]['span']
+print(f"Span: '{span_info['span_string']}' at {span_info['span_start']}-{span_info['span_end']}")
+```
+
+### Direct Usage (SimpleTransformers)
+
+```python
+from simpletransformers.question_answering import QuestionAnsweringModel
+
+model = QuestionAnsweringModel('xlmroberta', 'Futyn-Maker/ruscxn-span-predictor')
+
+# Format: context = Russian text, question = construction pattern
+to_predict = [
+    {
+        "context": "Что вам здесь нужно?",
+        "qas": [
+            {
+                "question": "что NP-Dat Cop нужно?",
+                "id": "0"
+            }
+        ]
+    }
+]
+
+predictions, _ = model.predict(to_predict)
+print(f"Predicted span: {predictions[0]['answer'][0]}")
+```
+
+## Training Data
+
+The model was trained on a question-answering dataset where:
+- **Context:** Russian text examples containing constructions
+- **Question:** Constructicon patterns
+- **Answer:** Text spans implementing the construction in the example
+
+## Output
+
+Returns the exact text span where a construction pattern is realized in the input text, including start and end character positions.
+
+## Framework Versions
+
+- SimpleTransformers: 0.70.1
+- Transformers: 4.51.3
+- PyTorch: 2.7.0+cu126

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555f23472de79eccb61a781dfac070d8fcc3dabdd69ce2af1493c2b812be519e
+size 1465

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef009ae2ede7beded780cfa82e11d2d977473cb6ddf9c3b5bdce3c367497fc01
+size 943862

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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
+    },
+    "35053": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f18b2f6f84f8705e92cda7c3c2f490e0a1e1443480f8fd56255bf62c267bdb7
+size 3921