upload

README.md

@@ -0,0 +1,52 @@
+---
+datasets:
+- multi_nli
+language: en
+license: mit
+pipeline_tag: zero-shot-classification
+tags:
+- bart
+- zero-shot-classification
+---
+# Bart large model for NLI-based Zero Shot Text Classification
+
+This model uses [bart-large](https://huggingface.co/facebook/bart-large).
+
+## Training Data
+This model was trained on the [MultiNLI (MNLI)](https://huggingface.co/datasets/multi_nli) dataset in the manner originally described in [Yin et al. 2019](https://arxiv.org/abs/1909.00161).
+
+It can be used to predict whether a topic label can be assigned to a given sequence, whether or not the label has been seen before.
+
+## Usage and Performance
+The trained model can be used like this:
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
+
+# Load model & tokenizer
+bart_model = AutoModelForSequenceClassification.from_pretrained('navteca/bart-large-mnli')
+bart_tokenizer = AutoTokenizer.from_pretrained('navteca/bart-large-mnli')
+
+# Get predictions
+nlp = pipeline('zero-shot-classification', model=bart_model, tokenizer=bart_tokenizer)
+
+sequence = 'One day I will see the world.'
+candidate_labels = ['cooking', 'dancing', 'travel']
+
+result = nlp(sequence, candidate_labels, multi_label=True)
+
+print(result)
+
+#{
+#  "sequence": "One day I will see the world.",
+#  "labels": [
+#    "travel",
+#    "dancing",
+#    "cooking"
+#  ],
+#  "scores": [
+#    0.9941897988319397,
+#    0.0060537424869835,
+#    0.0020010927692056
+#  ]
+#}
+```

config.json

@@ -0,0 +1,48 @@
+{
+  "_num_labels": 3,
+  "activation_dropout": 0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForSequenceClassification"
+  ],
+  "attention_dropout": 0,
+  "bos_token_id": 0,
+  "classif_dropout": 0,
+  "classifier_dropout": 0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 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,
+    "neutral": 1,
+    "entailment": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "normalize_before": false,
+  "num_hidden_layers": 12,
+  "output_past": false,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "use_cache": true,
+  "vocab_size": 50265
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e07d1ae73ae1c1267fd174a3b21c73b0d77bad288f8ed17fb685f79c419a897
+size 1629394629

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce253627f98f9db22af6a86efee6e905f001f7d8dc02dd14a8b4b4710c302b17
+size 1629486723

tokenizer_config.json

@@ -0,0 +1,3 @@
+{
+    "model_max_length": 1024
+}