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 +1,45 @@
+---
+tags: autonlp
+language: pt
+widget:
+- text: "I love AutoNLP 🤗"
+datasets:
+- Emanuel/autonlp-data-pos-tag-bosque
+co2_eq_emissions: 6.2107269129101805
+---
+
+# Model Trained Using AutoNLP
+
+- Problem type: Entity Extraction
+- Model ID: 21124427
+- CO2 Emissions (in grams): 6.2107269129101805
+
+## Validation Metrics
+
+- Loss: 0.09813392907381058
+- Accuracy: 0.9714309035997062
+- Precision: 0.9721275936822545
+- Recall: 0.9735345807918949
+- F1: 0.9728305785123967
+
+## 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/Emanuel/autonlp-pos-tag-bosque-21124427
+```
+
+Or Python API:
+
+```
+from transformers import AutoModelForTokenClassification, AutoTokenizer
+
+model = AutoModelForTokenClassification.from_pretrained("Emanuel/autonlp-pos-tag-bosque-21124427", use_auth_token=True)
+
+tokenizer = AutoTokenizer.from_pretrained("Emanuel/autonlp-pos-tag-bosque-21124427", use_auth_token=True)
+
+inputs = tokenizer("I love AutoNLP", return_tensors="pt")
+
+outputs = model(**inputs)
+```

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "AutoNLP",
+  "_num_labels": 17,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ADJ",
+    "1": "ADP",
+    "2": "ADV",
+    "3": "AUX",
+    "4": "CCONJ",
+    "5": "DET",
+    "6": "INTJ",
+    "7": "NOUN",
+    "8": "NUM",
+    "9": "PART",
+    "10": "PRON",
+    "11": "PROPN",
+    "12": "PUNCT",
+    "13": "SCONJ",
+    "14": "SYM",
+    "15": "VERB",
+    "16": "X"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ADJ": 0,
+    "ADP": 1,
+    "ADV": 2,
+    "AUX": 3,
+    "CCONJ": 4,
+    "DET": 5,
+    "INTJ": 6,
+    "NOUN": 7,
+    "NUM": 8,
+    "PART": 9,
+    "PRON": 10,
+    "PROPN": 11,
+    "PUNCT": 12,
+    "SCONJ": 13,
+    "SYM": 14,
+    "VERB": 15,
+    "X": 16
+  },
+  "layer_norm_eps": 1e-12,
+  "max_length": 256,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "padding": "max_length",
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.8.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d3a5ea467d3f5b2c089a47abd9a415c5c300695855accde27db91a7822d7de
+size 433465905

sample_input.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d45d00d14ef34d7969c5d9a31ecdbfae59404d9e11052cf64e2515609f11a799
+size 10084

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": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "AutoNLP", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}