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: unk
+widget:
+- text: "I love AutoNLP 🤗"
+datasets:
+- dee4hf/autonlp-data-shajBERT
+co2_eq_emissions: 11.98841452241473
+---
+
+# Model Trained Using AutoNLP
+
+- Problem type: Multi-class Classification
+- Model ID: 38639804
+- CO2 Emissions (in grams): 11.98841452241473
+
+## Validation Metrics
+
+- Loss: 0.421400249004364
+- Accuracy: 0.86783988957902
+- Macro F1: 0.8669477050676501
+- Micro F1: 0.86783988957902
+- Weighted F1: 0.86694770506765
+- Macro Precision: 0.867606300132228
+- Micro Precision: 0.86783988957902
+- Weighted Precision: 0.8676063001322278
+- Macro Recall: 0.86783988957902
+- Micro Recall: 0.86783988957902
+- Weighted Recall: 0.86783988957902
+
+
+## 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/dee4hf/autonlp-shajBERT-38639804
+```
+
+Or Python API:
+
+```
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+model = AutoModelForSequenceClassification.from_pretrained("dee4hf/autonlp-shajBERT-38639804", use_auth_token=True)
+
+tokenizer = AutoTokenizer.from_pretrained("dee4hf/autonlp-shajBERT-38639804", use_auth_token=True)
+
+inputs = tokenizer("I love AutoNLP", return_tensors="pt")
+
+outputs = model(**inputs)
+```

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "AutoNLP",
+  "_num_labels": 9,
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "communal_attack",
+    "1": "hate_speech",
+    "2": "inciteful",
+    "3": "personal_attack",
+    "4": "political_comment",
+    "5": "religious",
+    "6": "religious hatred",
+    "7": "religious_hatred",
+    "8": "suicidal_attack"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 4096,
+  "label2id": {
+    "communal_attack": 0,
+    "hate_speech": 1,
+    "inciteful": 2,
+    "personal_attack": 3,
+    "political_comment": 4,
+    "religious": 5,
+    "religious hatred": 6,
+    "religious_hatred": 7,
+    "suicidal_attack": 8
+  },
+  "layer_norm_eps": 1e-12,
+  "max_length": 64,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 16,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 24,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "padding": "max_length",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "transformers_version": "4.8.0",
+  "type_vocab_size": 2,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7b7ae4df344bbf935ab9f8c927b25482d40bffd2d4d0a6918790aa385ddb35
+size 71811793

sample_input.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084262e61159e827f14f672dd690e4ae18d86a172e25ccfa19ed65df25778a70
+size 2848

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": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "cls_token": "[CLS]", "pad_token": "<pad>", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "AutoNLP", "tokenizer_class": "PreTrainedTokenizerFast"}