Adding tweeteval classifier

README.md

@@ -0,0 +1,83 @@
+---
+language: english
+widget:
+- text: "Covid cases are increasing fast!"
+- text: "🤗"
+- text: "I hate you 🤮"
+---
+
+
+# Twitter-roBERTa-base for Sentiment Analysis
+
+This is a roBERTa-base model trained on ~200M tweets and finetuned for sentiment analysis with the TweetEval benchmark. This model is suitable for English.
+
+- Reference Paper: [_TweetEval_ (Findings of EMNLP 2020)](https://arxiv.org/pdf/2010.12421.pdf). 
+- Git Repo: [Tweeteval official repository](https://github.com/cardiffnlp/tweeteval).
+
+<b>Labels</b>: 
+0 -> Negative;
+1 -> Neutral;
+2 -> Positive
+
+## Example Pipeline
+```python
+from transformers import pipeline
+sentiment_task = pipeline("sentiment-analysis", model=model_path, tokenizer=model_path)
+sentiment_task("Covid cases are increasing fast!")
+```
+```
+[{'label': 'Negative', 'score': 0.7236}]
+```
+
+## Full classification example
+
+```python
+from transformers import AutoModelForSequenceClassification
+from transformers import TFAutoModelForSequenceClassification
+from transformers import AutoTokenizer, AutoConfig
+import numpy as np
+from scipy.special import softmax
+# Preprocess text (username and link placeholders)
+def preprocess(text):
+    new_text = []
+    for t in text.split(" "):
+        t = '@user' if t.startswith('@') and len(t) > 1 else t
+        t = 'http' if t.startswith('http') else t
+        new_text.append(t)
+    return " ".join(new_text)
+MODEL = f"cardiffnlp/twitter-roberta-base-sentiment-latest"
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
+config = AutoConfig.from_pretrained(MODEL)
+# PT
+model = AutoModelForSequenceClassification.from_pretrained(MODEL)
+#model.save_pretrained(MODEL)
+text = "Covid cases are increasing fast!"
+text = preprocess(text)
+encoded_input = tokenizer(text, return_tensors='pt')
+output = model(**encoded_input)
+scores = output[0][0].detach().numpy()
+scores = softmax(scores)
+# # TF
+# model = TFAutoModelForSequenceClassification.from_pretrained(MODEL)
+# model.save_pretrained(MODEL)
+# text = "Covid cases are increasing fast!"
+# encoded_input = tokenizer(text, return_tensors='tf')
+# output = model(encoded_input)
+# scores = output[0][0].numpy()
+# scores = softmax(scores)
+# Print labels and scores
+ranking = np.argsort(scores)
+ranking = ranking[::-1]
+for i in range(scores.shape[0]):
+    l = config.id2label[ranking[i]]
+    s = scores[ranking[i]]
+    print(f"{i+1}) {l} {np.round(float(s), 4)}")
+```
+
+Output: 
+
+```
+1) Negative 0.7236
+2) Neutral 0.2287
+3) Positive 0.0477
+```

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/home/jupyter/misc/tweeteval/TweetEval_models/sentiment/sentiment_latest_2021/",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Negative",
+    "1": "Neutral",
+    "2": "Positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Negative": 0,
+    "Neutral": 1,
+    "Positive": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}