Upload FinBERT-Multi

README.md

@@ -0,0 +1,58 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+tags:
+- text-classification
+- bert
+- finbert
+- finance
+- sentiment
+- sentiment-analysis
+- financial-sentiment
+datasets:
+- FinanceInc/auditor_sentiment
+- nickmuchi/financial-classification
+- warwickai/financial_phrasebank_mirror
+- NOSIBLE/financial-sentiment
+- TimKoornstra/financial-tweets-sentiment
+pipeline_tag: text-classification
+---
+
+# 🎯 FinBERT-Multi
+
+Financial sentiment analysis model. Fine-tuned [ProsusAI/finbert](https://huggingface.co/ProsusAI/finbert) on **143K+ samples** from 5 combined financial datasets.
+
+The model outputs softmax outputs for three sentiment classes: **Positive**, **Negative**, **Neutral**.
+
+## 🚀 Usage
+
+```python
+from transformers import pipeline
+
+classifier = pipeline("text-classification", model="ENTUM-AI/FinBERT-Multi")
+
+classifier("Stock price soars on record-breaking earnings report")
+# [{'label': 'Positive', 'score': 0.99}]
+
+classifier("Company announces quarterly earnings results")
+# [{'label': 'Neutral', 'score': 0.98}]
+
+classifier("Revenue decline signals weakening market position")
+# [{'label': 'Negative', 'score': 0.97}]
+```
+
+## 📊 Training Data
+
+| Dataset | Samples |
+|---------|---------|
+| [FinanceInc/auditor_sentiment](https://huggingface.co/datasets/FinanceInc/auditor_sentiment) | ~4.8K |
+| [nickmuchi/financial-classification](https://huggingface.co/datasets/nickmuchi/financial-classification) | ~5K |
+| [warwickai/financial_phrasebank_mirror](https://huggingface.co/datasets/warwickai/financial_phrasebank_mirror) | ~4.8K |
+| [NOSIBLE/financial-sentiment](https://huggingface.co/datasets/NOSIBLE/financial-sentiment) | ~100K |
+| [TimKoornstra/financial-tweets-sentiment](https://huggingface.co/datasets/TimKoornstra/financial-tweets-sentiment) | ~38K |
+
+## ⚠️ Limitations
+
+- English only

config.json

@@ -0,0 +1,40 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "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,
+  "is_decoder": false,
+  "label2id": {
+    "Negative": 0,
+    "Neutral": 1,
+    "Positive": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.1.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca760fd60c4883c1a4e536abfaf88faf653e01c4d3d56ad95ee0ed31b116798b
+size 437961700

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}