Initial

README.md

@@ -0,0 +1,31 @@
+---
+language: en
+tags:
+- text-classification
+- pytorch
+- tensorflow
+datasets:
+- ag_news
+license: mit
+widget
+- text: "Armed conflict has been a near-constant policial and economic burden."
+- text: "Tom Brady won his seventh Super Bowl last night."
+- text: "Dow falls more than 100 points after disappointing jobs data":
+- text: "A new moon has been discovered in Jupter's orbit."
+---
+
+# distilbert-base-uncased-agnews-student
+
+## Model Description
+
+This model is distilled from the zero-shot classification pipeline on the unlabeled AG's News dataset using [this
+script](https://github.com/huggingface/transformers/tree/master/examples/research_projects/zero-shot-distillation).
+It is the result of the demo notebook
+[here](https://colab.research.google.com/drive/1mjBjd0cR8G57ZpsnFCS3ngGyo5nCa9ya?usp=sharing), where more details
+about the model can be found.
+
+## Intended Usage
+
+The model can be used like any other model trained on AG's News, but will likely not perform as well as a model
+trained with full supervision. It is primarily intended as a demo of how an expensive NLI-based zero-shot model
+can be distilled to a more efficient student.

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "./distilbert-base-uncased-agnews-student/",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "the world",
+    "1": "sports",
+    "2": "business",
+    "3": "science/tech"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "business": 2,
+    "science/tech": 3,
+    "sports": 1,
+    "the world": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.4.0.dev0",
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae45738d2e01161bb5de6af060e043ef7e0592fc9b8ffd54bc7aeb9848c3cd30
+size 267866825

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6486c59cf836b7b62d40f010d619bbc45ff2ee316b3ca353e6751e5056b47a
+size 267958656

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "distilbert-base-uncased"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6004c90490755211a561ac7fd2c86ce8840a4fa12734cd4d493df54e07cc4b19
+size 2095