upload

CESoftmaxAccuracyEvaluator_AllNLI-dev_results.csv

@@ -0,0 +1,25 @@
+epoch,steps,Accuracy
+0,10000,0.9075138627460956
+0,20000,0.8990690339319326
+0,30000,0.9016635295314647
+0,40000,0.900137355649387
+0,50000,0.9045632599074122
+0,-1,0.9029862135625986
+1,10000,0.9057841990130743
+1,20000,0.9093961438673246
+1,30000,0.906547285954113
+1,40000,0.9111766800630818
+1,50000,0.9114310423767614
+1,-1,0.9131098336470469
+2,10000,0.9129572162588391
+2,20000,0.9115836597649692
+2,30000,0.9147377524545963
+2,40000,0.9150429872310119
+2,50000,0.9145342626036527
+2,-1,0.913720303199878
+3,10000,0.9127028539451595
+3,20000,0.9131607061097827
+3,30000,0.9142799002899731
+3,40000,0.916213053873938
+3,50000,0.9167726509640332
+3,-1,0.9172305031286565

README.md

@@ -0,0 +1,69 @@
+---
+language: en
+pipeline_tag: zero-shot-classification
+tags:
+- microsoft/deberta-v3-large
+datasets:
+- multi_nli
+- snli
+metrics:
+- accuracy
+license: apache-2.0
+---
+
+# Cross-Encoder for Natural Language Inference
+This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class. This model is based on [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large)
+
+## Training Data
+The model was trained on the [SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral.
+
+## Performance
+- Accuracy on SNLI-test dataset: 92.20
+- Accuracy on  MNLI mismatched set: 90.49
+
+For futher evaluation results, see [SBERT.net - Pretrained Cross-Encoder](https://www.sbert.net/docs/pretrained_cross-encoders.html#nli).
+
+## Usage
+
+Pre-trained models can be used like this:
+```python
+from sentence_transformers import CrossEncoder
+model = CrossEncoder('cross-encoder/nli-deberta-v3-large')
+scores = model.predict([('A man is eating pizza', 'A man eats something'), ('A black race car starts up in front of a crowd of people.', 'A man is driving down a lonely road.')])
+
+#Convert scores to labels
+label_mapping = ['contradiction', 'entailment', 'neutral']
+labels = [label_mapping[score_max] for score_max in scores.argmax(axis=1)]
+```
+
+## Usage with Transformers AutoModel
+You can use the model also directly with Transformers library (without SentenceTransformers library):
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+model = AutoModelForSequenceClassification.from_pretrained('cross-encoder/nli-deberta-v3-large')
+tokenizer = AutoTokenizer.from_pretrained('cross-encoder/nli-deberta-v3-large')
+
+features = tokenizer(['A man is eating pizza', 'A black race car starts up in front of a crowd of people.'], ['A man eats something', 'A man is driving down a lonely road.'],  padding=True, truncation=True, return_tensors="pt")
+
+model.eval()
+with torch.no_grad():
+    scores = model(**features).logits
+    label_mapping = ['contradiction', 'entailment', 'neutral']
+    labels = [label_mapping[score_max] for score_max in scores.argmax(dim=1)]
+    print(labels)
+```
+
+## Zero-Shot Classification
+This model can also be used for zero-shot-classification:
+```python
+from transformers import pipeline
+
+classifier = pipeline("zero-shot-classification", model='cross-encoder/nli-deberta-v3-large')
+
+sent = "Apple just announced the newest iPhone X"
+candidate_labels = ["technology", "sports", "politics"]
+res = classifier(sent, candidate_labels)
+print(res)
+``` 

added_tokens.json

@@ -0,0 +1 @@
+{"[MASK]": 128000}

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "contradiction",
+    "1": "entailment",
+    "2": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "contradiction": 0,
+    "entailment": 1,
+    "neutral": 2
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c33255910cf2783a71731b2798bec3732f6ad9585682bea7c8233608e4c7d34
+size 1740435986

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "sp_model_kwargs": {}, "vocab_type": "spm", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/deberta-v3-large", "tokenizer_class": "DebertaV2Tokenizer", "model_max_length": 512}