Add files using upload-large-folder tool

.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 +1,306 @@
+---
+language:
+- en
+- zh
+- ja
+- es
+- de
+- fr
+- ar
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-classification
+base_model: FacebookAI/xlm-roberta-large
+datasets:
+- Kenpache/financial-sentiment-eval-7lang
+metrics:
+- accuracy
+- f1
+tags:
+- finance
+- financial-sentiment
+- sentiment-analysis
+- multilingual
+- financial-news
+- fintech
+- trading
+- market-sentiment
+- text-classification
+- xlm-roberta
+- cross-lingual
+---
+
+# Financial Sentiment, 7 Languages — Large
+
+**Sentiment of financial news, in seven languages, from one model.** Feed it a headline
+or a sentence in English, Chinese, Japanese, Spanish, German, French or Arabic — get
+back `negative`, `neutral` or `positive`.
+
+```python
+from transformers import pipeline
+
+clf = pipeline("text-classification", model="Kenpache/finbert-multilingual-v2-large")
+
+clf("The company reported record quarterly earnings, driven by strong demand.")
+# [{'label': 'positive', 'score': 0.9445}]
+
+clf("Die Aktie verlor nach der Gewinnwarnung deutlich an Wert.")
+# [{'label': 'negative', 'score': 0.9435}]
+
+clf("该公司宣布大规模裁员计划，股价应声下跌。")
+# [{'label': 'negative', 'score': 0.9436}]
+```
+
+| | |
+|---|---|
+| **Task** | Financial sentiment, 3 classes (negative / neutral / positive) |
+| **Languages** | **7** — en · zh · ja · es · de · fr · ar |
+| **Accuracy** | **88.9%** |
+| **Parameters** | 560M (fp32, 2.1 GB) |
+| **Backbone** | [`FacebookAI/xlm-roberta-large`](https://huggingface.co/FacebookAI/xlm-roberta-large) |
+
+One model covers all seven languages — no per-language checkpoints, no translation step,
+no language ID in front of it. Mixed-language pipelines just work.
+
+**Smaller sibling:**
+[`Kenpache/finbert-multilingual-v2`](https://huggingface.co/Kenpache/finbert-multilingual-v2)
+— 307M parameters, 87.2% on the same evaluation set. Take this one for accuracy, that
+one for footprint.
+
+---
+
+## Accuracy
+
+Measured on a held-out test set of **4,993 financial news sentences** across the seven
+languages, published as
+[`Kenpache/financial-sentiment-eval-7lang`](https://huggingface.co/datasets/Kenpache/financial-sentiment-eval-7lang).
+
+| Metric | Score |
+|---|---|
+| **Accuracy** | **0.8892** |
+| **F1 (weighted)** | **0.8890** |
+
+### Per language
+
+This is the table to read before adopting the model — it tells you whether *your*
+language is covered properly, not just the average.
+
+| Language | | Items | Accuracy |
+|---|---|---:|---:|
+| Spanish | `es` | 905 | **0.9193** |
+| German | `de` | 650 | **0.9062** |
+| Chinese | `zh` | 1,023 | 0.8974 |
+| Arabic | `ar` | 73 | 0.8904 |
+| Japanese | `ja` | 1,063 | 0.8852 |
+| English | `en` | 780 | 0.8615 |
+| French | `fr` | 499 | 0.8477 |
+
+**Every one of the seven languages is above 84%**, and English is not at the top —
+Spanish and German are. That matters more than it looks: most "multilingual" financial
+models are English models with a multilingual tokenizer, and they collapse on CJK and
+right-to-left text. This one holds its level across scripts — Latin, Chinese, Japanese
+and Arabic alike.
+
+Arabic is measured on 73 items, so treat its number as indicative rather than precise.
+
+### Reproducing these numbers
+
+The evaluation set is public, and so is the protocol — `max_length=192`, fp32, raw text
+with no normalisation:
+
+```python
+import pandas as pd, torch
+from datasets import load_dataset
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+ds = load_dataset("Kenpache/financial-sentiment-eval-7lang", split="test").to_pandas()
+
+REPO = "Kenpache/finbert-multilingual-v2-large"
+tok = AutoTokenizer.from_pretrained(REPO)
+model = AutoModelForSequenceClassification.from_pretrained(REPO).eval()
+
+preds = []
+with torch.no_grad():
+    for i in range(0, len(ds), 64):
+        enc = tok(ds.sentence[i:i + 64].tolist(), return_tensors="pt",
+                  padding=True, truncation=True, max_length=192)
+        preds += [model.config.id2label[j].lower()
+                  for j in model(**enc).logits.argmax(-1).tolist()]
+
+print((pd.Series(preds) == ds.label).mean())   # 0.8892
+```
+
+### Per class
+
+| Class | Precision | Recall | F1 | Support |
+|---|---:|---:|---:|---:|
+| negative | 0.8820 | 0.9135 | 0.8975 | 1,260 |
+| neutral | 0.9049 | 0.8508 | 0.8770 | 2,158 |
+| positive | 0.8758 | 0.9225 | 0.8986 | 1,575 |
+
+No class collapse: the three F1 scores sit within 2.2 points of each other, and `neutral`
+— the majority class, and the usual dumping ground for models that learned to hedge — has
+the *lowest* F1 of the three rather than the highest.
+
+**Polarity errors are rare.** Across all 4,993 items, `negative` is called `positive` 14
+times and `positive` is called `negative` 24 times — **38 cases, 0.8% of the set**.
+Practically all remaining error sits on the boundary with `neutral`. The model may fail to
+register a weak signal; it very seldom reverses one.
+
+### Comparison on the English subset
+
+Both models were run on the **English portion — 780 items — of
+[`Kenpache/financial-sentiment-eval-7lang`](https://huggingface.co/datasets/Kenpache/financial-sentiment-eval-7lang)**,
+under one identical protocol: `max_length=192`, fp32, raw text, argmax over the three
+classes, no tuning or threshold fitting for either model.
+
+| Model | Accuracy | F1 (weighted) |
+|---|---:|---:|
+| **This model** | **0.8615** | **0.8616** |
+| [`ProsusAI/finbert`](https://huggingface.co/ProsusAI/finbert) | 0.7218 | 0.7224 |
+
+Two things belong next to those numbers. `ProsusAI/finbert` is an English-only model, so
+the comparison is confined to the English subset — which is, as the table above shows,
+this model's weakest language of the seven. And it was trained under a different
+annotation convention: most of its errors on this set are neutral items assigned a
+direction, so part of the gap reflects differing label conventions rather than capability.
+
+**These figures describe behaviour on this evaluation set only, under the protocol stated
+above. They are not a general claim about either model.**
+
+---
+
+## Usage
+
+```bash
+pip install transformers torch
+```
+
+### Pipeline
+
+```python
+from transformers import pipeline
+
+clf = pipeline("text-classification", model="Kenpache/finbert-multilingual-v2-large")
+
+clf("Les bénéfices du groupe ont augmenté de 15% au premier trimestre.")
+# [{'label': 'positive', 'score': 0.9443}]
+```
+
+Batch a whole list in one call:
+
+```python
+texts = ["株価は決算発表後に急落した。",
+         "La compañía anunció un despido masivo y sus acciones se desplomaron.",
+         "Quarterly revenue beat analyst expectations by a wide margin."]
+
+clf(texts, batch_size=32)
+# [{'label': 'negative', 'score': 0.9458},
+#  {'label': 'negative', 'score': 0.9462},
+#  {'label': 'positive', 'score': 0.9467}]
+```
+
+Add `top_k=None` to get the full probability distribution over all three classes instead
+of the winner only — useful when you want to threshold on confidence rather than take
+the argmax.
+
+### Direct loading
+
+```python
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+REPO = "Kenpache/finbert-multilingual-v2-large"
+tokenizer = AutoTokenizer.from_pretrained(REPO)
+model = AutoModelForSequenceClassification.from_pretrained(REPO).eval()
+
+text = "Der Umsatz blieb im Vergleich zum Vorjahr unverändert."
+enc = tokenizer(text, return_tensors="pt", truncation=True, max_length=192)
+
+with torch.no_grad():
+    probs = torch.softmax(model(**enc).logits, dim=-1)[0]
+
+for i, p in enumerate(probs):
+    print(f"{model.config.id2label[i]:8} {p:.4f}")
+
+# negative 0.0234
+# neutral  0.9491
+# positive 0.0275
+```
+
+### On GPU
+
+```python
+clf = pipeline("text-classification", model=REPO, device=0)          # CUDA
+clf = pipeline("text-classification", model=REPO, device="mps")      # Apple Silicon
+```
+
+CUDA, Apple Silicon and plain CPU all work. At 560M parameters inference is comfortable
+on a laptop, though noticeably heavier than the 307M sibling.
+
+**Use `max_length=192`** to reproduce the numbers above. The hard ceiling of the backbone
+is 512 tokens — enough for headlines and single sentences, which is what this model is
+for, but do not expect it to take long documents.
+
+---
+
+## Limitations
+
+1. **Sentence-level, not document-level.** The model is built for headlines and single
+   sentences. Feeding a full article gives you one label for the whole thing, which is
+   rarely what you want — split it first. The 512-token ceiling enforces this anyway.
+2. **Financial sentiment is not general sentiment.** "Shares fell 3% on the news" is
+   negative in a market sense with no emotional language at all. On product reviews or
+   social media this model is the wrong tool.
+3. **`neutral` is a convention, not a fact.** The boundary between neutral and mildly
+   positive/negative is where human annotators disagree most, and the model inherits that
+   ambiguity. If a decision hinges on that boundary, use the probabilities and a
+   threshold instead of the argmax.
+4. **Arabic coverage is thin** in evaluation (73 items). The other six languages are
+   measured on 499–1,063 items each.
+5. **Seven languages.** The backbone is pretrained on a hundred, but this classifier was
+   tuned for these seven. Other languages will produce output, but it is untested.
+6. **Not investment advice.** The output is a sentiment label on a text, not a signal to
+   trade on.
+
+---
+
+## Intended use
+
+Good fits:
+
+- tagging multilingual financial news feeds in real time
+- market-sentiment dashboards and indices across regions
+- pre-screening research corpora before human analysis
+- backtesting sentiment-based features on multilingual sources
+
+Poor fits: general-purpose sentiment, long documents, languages outside the seven,
+anything where the neutral boundary carries legal or financial weight on its own.
+
+---
+
+## Files
+
+| File | What it is |
+|---|---|
+| `model.safetensors` | weights, fp32, 2.1 GB |
+| `config.json` | XLM-RoBERTa config with `id2label` (`negative` / `neutral` / `positive`) |
+| `tokenizer.json`, `sentencepiece.bpe.model`, `tokenizer_config.json` | tokenizer |
+
+## License
+
+Apache 2.0.
+
+Built on [`FacebookAI/xlm-roberta-large`](https://huggingface.co/FacebookAI/xlm-roberta-large),
+which is MIT-licensed; that attribution is preserved here.
+
+## Citation
+
+```bibtex
+@misc{finbert_multilingual_v2_large,
+  title  = {Financial Sentiment, 7 Languages — Large},
+  author = {Kenpache},
+  year   = {2026},
+  url    = {https://huggingface.co/Kenpache/finbert-multilingual-v2-large}
+}
+```

config.json

@@ -0,0 +1,40 @@
+{
+  "add_cross_attention": false,
+  "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": 1024,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "is_decoder": false,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "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",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.15.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ffaa1fc09c21e4d77835bf1ebb2c12c89d7cd2168ab5d2a0098a20221565c8
+size 2239622772

sentencepiece.bpe.model

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ffc61f7cb57aa8c419fa9d2409c2af1abf4a92ba5a12c60a09cafa5a59c9b1
+size 17098184

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": true,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}