Upload folder using huggingface_hub

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,43 @@
+---
+language:
+- ru
+license: apache-2.0
+base_model: cointegrated/rubert-tiny2
+tags:
+- finance
+- sentiment-analysis
+- russian
+datasets:
+- apkonsta/FinancialPhraseBank-v1.0-ru
+metrics:
+- accuracy
+- f1
+---
+
+# FinRuBERT
+
+Fine-tuned модель для анализа тональности финансовых текстов на русском языке.
+
+## Описание
+Модель была дообучена на датасете FinancialPhraseBank (русская версия) и предсказывает:
+- **Негативный** (`negative`)
+- **Нейтральный** (`neutral`)
+- **Позитивный** (`positive`)
+
+## Данные обучения
+Использовалась версия датасета с согласием аннотаторов ≥50% (4,840 примеров):
+- Sentences_50Agree.csv из [FinancialPhraseBank-v1.0-ru](https://huggingface.co/datasets/apkonsta/FinancialPhraseBank-v1.0-ru)
+
+## Использование
+
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
+
+model_name = "apkonsta/finrubert"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)
+result = classifier("Прибыль компании сократилась на 15% в этом квартале")
+
+print(result)  # [{'label': 'negative', 'score': 0.88}]

README.md

@@ -1,3 +1,43 @@
----
-license: apache-2.0
----
+---
+language:
+- ru
+license: apache-2.0
+base_model: cointegrated/rubert-tiny2
+tags:
+- finance
+- sentiment-analysis
+- russian
+datasets:
+- apkonsta/FinancialPhraseBank-v1.0-ru
+metrics:
+- accuracy
+- f1
+---
+
+# FinRuBERT
+
+Fine-tuned модель для анализа тональности финансовых текстов на русском языке.
+
+## Описание
+Модель была дообучена на датасете FinancialPhraseBank (русская версия) и предсказывает:
+- **Негативный** (`negative`)
+- **Нейтральный** (`neutral`)
+- **Позитивный** (`positive`)
+
+## Данные обучения
+Использовалась версия датасета с согласием аннотаторов ≥50% (4,840 примеров):
+- Sentences_50Agree.csv из [FinancialPhraseBank-v1.0-ru](https://huggingface.co/datasets/apkonsta/FinancialPhraseBank-v1.0-ru)
+
+## Использование
+
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
+
+model_name = "apkonsta/finrubert"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)
+result = classifier("Прибыль компании сократилась на 15% в этом квартале")
+
+print(result)  # [{'label': 'negative', 'score': 0.88}]

config.json

@@ -0,0 +1 @@
+{"return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "float32", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["BertForPreTraining"], "finetuning_task": null, "id2label": {"0": "positive", "1": "negative", "2": "neutral"}, "label2id": {"positive": 0, "negative": 1, "neutral": 2}, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "pad_token_id": 0, "eos_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "/home/jupyter-anikolaeva/finrubert/finBERT/models/classifier_model/finbert-sentiment", "_attn_implementation_autoset": true, "transformers_version": "4.50.0.dev0", "emb_size": 312, "gradient_checkpointing": false, "model_type": "bert", "vocab_size": 83828, "hidden_size": 312, "num_hidden_layers": 3, "num_attention_heads": 12, "hidden_act": "gelu", "intermediate_size": 600, "hidden_dropout_prob": 0.1, "attention_probs_dropout_prob": 0.1, "max_position_embeddings": 2048, "type_vocab_size": 2, "initializer_range": 0.02, "layer_norm_eps": 1e-12, "position_embedding_type": "absolute", "use_cache": true, "classifier_dropout": null}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2864f11397ec0a304dc62b3dbd94bc04875f131affb0e55adc6f7ea9fc2e7fcb
+size 116801241

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "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 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 2048,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}