Initial upload of go_emotions

README.md

@@ -0,0 +1,23 @@
+---
+license: mit
+---
+
+[joeddav/distilbert-base-uncased-go-emotions-student](https://huggingface.co/joeddav/distilbert-base-uncased-go-emotions-student) converted to ONNX and quantized using optimum.
+
+---
+
+# distilbert-base-uncased-go-emotions-student
+
+## Model Description
+
+This model is distilled from the zero-shot classification pipeline on the unlabeled GoEmotions dataset using [this
+script](https://github.com/huggingface/transformers/tree/master/examples/research_projects/zero-shot-distillation).
+It was trained with mixed precision for 10 epochs and otherwise used the default script arguments. 
+
+## Intended Usage
+
+The model can be used like any other model trained on GoEmotions, 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, allowing a classifier to be trained with only unlabeled data. Note
+that although the GoEmotions dataset allow multiple labels per instance, the teacher used single-label 
+classification to create psuedo-labels.

config.json

@@ -0,0 +1,83 @@
+{
+  "_name_or_path": "joeddav/distilbert-base-uncased-go-emotions-student",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "admiration",
+    "1": "amusement",
+    "2": "anger",
+    "3": "annoyance",
+    "4": "approval",
+    "5": "caring",
+    "6": "confusion",
+    "7": "curiosity",
+    "8": "desire",
+    "9": "disappointment",
+    "10": "disapproval",
+    "11": "disgust",
+    "12": "embarrassment",
+    "13": "excitement",
+    "14": "fear",
+    "15": "gratitude",
+    "16": "grief",
+    "17": "joy",
+    "18": "love",
+    "19": "nervousness",
+    "20": "optimism",
+    "21": "pride",
+    "22": "realization",
+    "23": "relief",
+    "24": "remorse",
+    "25": "sadness",
+    "26": "surprise",
+    "27": "neutral"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "admiration": 0,
+    "amusement": 1,
+    "anger": 2,
+    "annoyance": 3,
+    "approval": 4,
+    "caring": 5,
+    "confusion": 6,
+    "curiosity": 7,
+    "desire": 8,
+    "disappointment": 9,
+    "disapproval": 10,
+    "disgust": 11,
+    "embarrassment": 12,
+    "excitement": 13,
+    "fear": 14,
+    "gratitude": 15,
+    "grief": 16,
+    "joy": 17,
+    "love": 18,
+    "nervousness": 19,
+    "neutral": 27,
+    "optimism": 20,
+    "pride": 21,
+    "realization": 22,
+    "relief": 23,
+    "remorse": 24,
+    "sadness": 25,
+    "surprise": 26
+  },
+  "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": "4.34.0.dev0",
+  "vocab_size": 30522
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036f30ecf2408e929a88e74bbdb0093b09cf2a43a1406065e0a6fa09c10c5410
+size 268035690

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4a425c70f9dc0f2da1d0cacd6fc4c6008e85bb8961fe62de46bd9e44cde464
+size 67601404

quantize_config.json

@@ -0,0 +1,35 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Unsqueeze",
+                "Reshape",
+                "Erf",
+                "Cast",
+                "Pow",
+                "Softmax",
+                "Transpose",
+                "Relu",
+                "Div",
+                "Gather",
+                "Shape",
+                "Slice",
+                "Gemm",
+                "Concat",
+                "Mul",
+                "Sqrt",
+                "MatMul",
+                "Constant",
+                "ReduceMean",
+                "Sub",
+                "Add",
+                "Expand",
+                "Where",
+                "Equal"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}