Commit From AutoNLP

.gitattributes

@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,52 @@
+---
+tags: autonlp
+language: en
+widget:
+- text: "I love AutoNLP 🤗"
+datasets:
+- madhurjindal/autonlp-data-Gibberish-Detector
+co2_eq_emissions: 5.527544460835904
+---
+
+# Model Trained Using AutoNLP
+
+- Problem type: Multi-class Classification
+- Model ID: 492513457
+- CO2 Emissions (in grams): 5.527544460835904
+
+## Validation Metrics
+
+- Loss: 0.07609463483095169
+- Accuracy: 0.9735624586913417
+- Macro F1: 0.9736173135739408
+- Micro F1: 0.9735624586913417
+- Weighted F1: 0.9736173135739408
+- Macro Precision: 0.9737771415197378
+- Micro Precision: 0.9735624586913417
+- Weighted Precision: 0.9737771415197378
+- Macro Recall: 0.9735624586913417
+- Micro Recall: 0.9735624586913417
+- Weighted Recall: 0.9735624586913417
+
+
+## Usage
+
+You can use cURL to access this model:
+
+```
+$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoNLP"}' https://api-inference.huggingface.co/models/madhurjindal/autonlp-Gibberish-Detector-492513457
+```
+
+Or Python API:
+
+```
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+model = AutoModelForSequenceClassification.from_pretrained("madhurjindal/autonlp-Gibberish-Detector-492513457", use_auth_token=True)
+
+tokenizer = AutoTokenizer.from_pretrained("madhurjindal/autonlp-Gibberish-Detector-492513457", use_auth_token=True)
+
+inputs = tokenizer("I love AutoNLP", return_tensors="pt")
+
+outputs = model(**inputs)
+```

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "AutoNLP",
+  "_num_labels": 4,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "clean",
+    "1": "mild gibberish",
+    "2": "noise",
+    "3": "word salad"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "clean": 0,
+    "mild gibberish": 1,
+    "noise": 2,
+    "word salad": 3
+  },
+  "max_length": 64,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "padding": "max_length",
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6b3f193eb8bca34495fb733d1187dcbc1ee4a03327396f609fd384f6d62d19
+size 267866225

sample_input.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be88e587f6b9b4ada6406c0ccb4d9a9eb199fb025cf4bb245d43e97662543603
+size 2034

special_tokens_map.json

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

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, "special_tokens_map_file": null, "name_or_path": "AutoNLP", "tokenizer_class": "DistilBertTokenizer"}