Upload 8 files

.gitattributes

@@ -0,0 +1,10 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,115 @@
+---
+license: mit
+pipeline_tag: zero-shot-classification
+tags:
+- zero-shot
+- nli
+- classification
+- bart
+- Coral
+datasets:
+- multi_nli
+base_model:
+- facebook/bart-large-mnli
+---
+
+***Coral-MNLI***
+
+**Coral-MNLI** is a high-quality zero-shot classification model based on BART-large, fine-tuned on MultiNLI.
+
+It delivers strong performance for zero-shot and few-shot text classification without any task-specific training.
+
+## What it is good at
+
+- Zero-shot text classification
+- Multi-label classification
+- Natural Language Inference (NLI)
+- Topic detection, sentiment, intent, content moderation, and many other classification tasks
+
+Just provide the text and a list of candidate labels — the model ranks them by how well they fit.
+
+## Model Details
+
+| Property                  | Value                          |
+|---------------------------|--------------------------------|
+| Architecture              | BART-large                     |
+| Task                      | Sequence Classification (NLI)  |
+| Labels                    | contradiction / neutral / entailment |
+| Max Sequence Length       | 1024                           |
+| Vocabulary Size           | 50,265                         |
+| License                   | MIT                            |
+
+## Quick Start
+
+### Using the Pipeline (recommended)
+
+```python
+from transformers import pipeline
+
+classifier = pipeline(
+    "zero-shot-classification",
+    model="path/to/Coral-MNLI"
+)
+
+sequence = "One day I will see the world"
+candidate_labels = ["travel", "cooking", "dancing"]
+
+result = classifier(sequence, candidate_labels)
+print(result)
+```
+
+### Multi-label mode
+
+```python
+result = classifier(
+    sequence,
+    candidate_labels=["travel", "cooking", "dancing", "exploration"],
+    multi_label=True
+)
+```
+
+### Manual usage
+
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+
+model = AutoModelForSequenceClassification.from_pretrained("path/to/Coral-MNLI")
+tokenizer = AutoTokenizer.from_pretrained("path/to/Coral-MNLI")
+
+premise = "One day I will see the world"
+label = "travel"
+hypothesis = f"This example is {label}."
+
+inputs = tokenizer(premise, hypothesis, return_tensors="pt", truncation=True)
+with torch.no_grad():
+    logits = model(**inputs).logits
+
+# Take only contradiction (0) and entailment (2)
+probs = torch.softmax(logits[:, [0, 2]], dim=1)
+prob_label_is_true = probs[0, 1].item()
+print(f"Probability that the text is about '{label}': {prob_label_is_true:.4f}")
+```
+
+## How Zero-Shot Classification works
+
+The model treats the input text as a **premise** and turns each candidate label into a **hypothesis** of the form:
+
+> "This example is {label}."
+
+It then uses the entailment probability as the score for that label. This simple trick works surprisingly well across many domains.
+
+## Tips for best results
+
+- Use clear and specific labels
+- Prefer multi_label=True when several labels can be true at the same time
+- For short texts the model is usually very accurate
+- For very long texts, keep the most important part near the beginning (truncation keeps the start)
+
+## License
+
+MIT
+
+## Credits
+
+Based on the excellent [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli) model.

config.json

@@ -0,0 +1,49 @@
+{
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "contradiction",
+    "1": "neutral",
+    "2": "entailment"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "contradiction": 0,
+    "entailment": 2,
+    "neutral": 1
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "normalize_before": false,
+  "num_hidden_layers": 12,
+  "output_past": false,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "transformers_version": "4.7.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

gitattributes

@@ -0,0 +1,10 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfbb687dbbd9df99fe865e1860350a22aebac4d26ee4bcb50217f1df606a018e
+size 1629437147

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "model_max_length": 1024,
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>",
+  "mask_token": "<mask>",
+  "tokenizer_class": "BartTokenizer"
+}