Upload 8 files

README.md

@@ -0,0 +1,114 @@
+---
+language: multilingual
+widget:
+- text: "🤗"
+- text: "T'estimo! ❤️"
+- text: "I love you!"
+- text: "I hate you 🤮"
+- text: "Mahal kita!"
+- text: "사랑해!"
+- text: "난 너가 싫어"
+- text: "😍😍😍"
+---
+
+
+# twitter-XLM-roBERTa-base for Sentiment Analysis
+
+This is a multilingual XLM-roBERTa-base model trained on ~198M tweets and finetuned for sentiment analysis. The sentiment fine-tuning was done on 8 languages (Ar, En, Fr, De, Hi, It, Sp, Pt) but it can be used for more languages (see paper for details).
+
+- Paper: [XLM-T: A Multilingual Language Model Toolkit for Twitter](https://arxiv.org/abs/2104.12250). 
+- Git Repo: [XLM-T official repository](https://github.com/cardiffnlp/xlm-t).
+
+This model has been integrated into the [TweetNLP library](https://github.com/cardiffnlp/tweetnlp).
+
+## Example Pipeline
+```python
+from transformers import pipeline
+model_path = "cardiffnlp/twitter-xlm-roberta-base-sentiment"
+sentiment_task = pipeline("sentiment-analysis", model=model_path, tokenizer=model_path)
+sentiment_task("T'estimo!")
+```
+```
+[{'label': 'Positive', 'score': 0.6600581407546997}]
+```
+
+## 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-xlm-roberta-base-sentiment"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
+config = AutoConfig.from_pretrained(MODEL)
+
+# 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)
+
+# 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) Positive 0.7673
+2) Neutral 0.2015
+3) Negative 0.0313
+```
+
+### Reference
+```
+@inproceedings{barbieri-etal-2022-xlm,
+    title = "{XLM}-{T}: Multilingual Language Models in {T}witter for Sentiment Analysis and Beyond",
+    author = "Barbieri, Francesco  and
+      Espinosa Anke, Luis  and
+      Camacho-Collados, Jose",
+    booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
+    month = jun,
+    year = "2022",
+    address = "Marseille, France",
+    publisher = "European Language Resources Association",
+    url = "https://aclanthology.org/2022.lrec-1.27",
+    pages = "258--266"
+}
+
+```
+

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/home/jupyter/misc/tweeteval/TweetEval_models/xlm-twitter/local-twitter-xlm-roberta-base-sentiment/",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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": "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": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "type_vocab_size": 1,
+  "vocab_size": 250002
+}

gitattributes

@@ -0,0 +1,16 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite 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
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93316a86051c359748c5d5453e7660c69a21a57cfb477892f95f539e3e171196
+size 1112271561

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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>"}

test1.ipynb

@@ -0,0 +1,102 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "b7da4b7f-babc-47ab-82bb-cfd31c2531e0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoConfig\n",
+    "from scipy.special import softmax\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2e109896-aba6-464b-805b-2f87dc4f61c4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'transformers.models.xlm_roberta.tokenization_xlm_roberta_fast.XLMRobertaTokenizerFast'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "import sentencepiece\n",
+    "from transformers import AutoTokenizer\n",
+    "\n",
+    "tokenizer = AutoTokenizer.from_pretrained(\n",
+    "    r\"C:\\Users\\frann\\Downloads\\sentiment-analysis\"\n",
+    ")\n",
+    "print(type(tokenizer))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "46f22dfc-a6b1-4fa1-9bee-ad1718fd8108",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "positive: 0.9313\n",
+      "neutral: 0.0408\n",
+      "negative: 0.0279\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import AutoModelForSequenceClassification, AutoConfig\n",
+    "from scipy.special import softmax\n",
+    "\n",
+    "local = r\"C:\\Users\\frann\\Downloads\\sentiment-analysis\"\n",
+    "tokenizer = AutoTokenizer.from_pretrained(local, use_fast=False)\n",
+    "config = AutoConfig.from_pretrained(local)\n",
+    "model = AutoModelForSequenceClassification.from_pretrained(local)\n",
+    "\n",
+    "text = \"j'ai été très ému \"\n",
+    "inputs = tokenizer(text, return_tensors=\"pt\")\n",
+    "outputs = model(**inputs)\n",
+    "scores = softmax(outputs.logits.detach().numpy()[0])\n",
+    "\n",
+    "for idx in scores.argsort()[::-1]:\n",
+    "    print(f\"{config.id2label[idx]}: {scores[idx]:.4f}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e4a1bb6a-4c8f-40df-97f9-69f2506e5b6f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c751d49a0c68a9d14ef218053b1baee3d5713dc6d22ca7ec05486f9337cdf1
+size 1114822968