Model

.gitattributes

@@ -1,35 +1,9 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,119 @@
+---
+datasets:
+- tweet_eval
+language:
+- en
+---
+# Twitter-roBERTa-base for Sentiment Analysis
+
+This is a roBERTa-base model trained on ~58M tweets and finetuned for sentiment analysis with the TweetEval benchmark. This model is suitable for English (for a similar multilingual model, see [XLM-T](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment)).
+
+- 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
+
+<b>New!</b> We just released a new sentiment analysis model trained on more recent and a larger quantity of tweets. 
+See [twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) and [TweetNLP](https://tweetnlp.org) for more details.
+
+## Example of classification
+
+```python
+from transformers import AutoModelForSequenceClassification
+from transformers import TFAutoModelForSequenceClassification
+from transformers import AutoTokenizer
+import numpy as np
+from scipy.special import softmax
+import csv
+import urllib.request
+
+# 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)
+
+# Tasks:
+# emoji, emotion, hate, irony, offensive, sentiment
+# stance/abortion, stance/atheism, stance/climate, stance/feminist, stance/hillary
+
+task='sentiment'
+MODEL = f"cardiffnlp/twitter-roberta-base-{task}"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
+
+# download label mapping
+labels=[]
+mapping_link = f"https://raw.githubusercontent.com/cardiffnlp/tweeteval/main/datasets/{task}/mapping.txt"
+with urllib.request.urlopen(mapping_link) as f:
+    html = f.read().decode('utf-8').split("\n")
+    csvreader = csv.reader(html, delimiter='\t')
+labels = [row[1] for row in csvreader if len(row) > 1]
+
+# PT
+model = AutoModelForSequenceClassification.from_pretrained(MODEL)
+model.save_pretrained(MODEL)
+
+text = "Good night 😊"
+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 = "Good night 😊"
+# encoded_input = tokenizer(text, return_tensors='tf')
+# output = model(encoded_input)
+# scores = output[0][0].numpy()
+# scores = softmax(scores)
+
+ranking = np.argsort(scores)
+ranking = ranking[::-1]
+for i in range(scores.shape[0]):
+    l = labels[ranking[i]]
+    s = scores[ranking[i]]
+    print(f"{i+1}) {l} {np.round(float(s), 4)}")
+
+```
+
+Output: 
+
+```
+1) positive 0.8466
+2) neutral 0.1458
+3) negative 0.0076
+```
+
+### BibTeX entry and citation info
+
+Please cite the [reference paper](https://aclanthology.org/2020.findings-emnlp.148/) if you use this model.
+
+```bibtex
+@inproceedings{barbieri-etal-2020-tweeteval,
+    title = "{T}weet{E}val: Unified Benchmark and Comparative Evaluation for Tweet Classification",
+    author = "Barbieri, Francesco  and
+      Camacho-Collados, Jose  and
+      Espinosa Anke, Luis  and
+      Neves, Leonardo",
+    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
+    month = nov,
+    year = "2020",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2020.findings-emnlp.148",
+    doi = "10.18653/v1/2020.findings-emnlp.148",
+    pages = "1644--1650"
+}
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "tweeteval_new/roberta-base-rt-sentiment/",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 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,
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d892ae550c152fd6175b7be9841cd9d3509ae80ea4b0aefe28ba41ea610d4d
+size 498598977

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37a3484c55954cd75b336a85f1e0c023ae874f3a73b05d2418dd04828e293b1
+size 498679497

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": "<mask>"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60edb4641e2b28ee3ecfb272f96cb9a6b0a662f4072eaf294dd8a1fd8b8484f3
+size 501229896