add files

.gitattributes

@@ -29,3 +29,4 @@ 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
+*.m filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,82 @@
+---
+language: english
+widget:
+- text: "Covid cases are increasing fast!"
+---
+
+
+# Twitter-roBERTa-base for Sentiment Analysis - UPDATED (2021)
+
+This is a roBERTa-base model trained on ~124M tweets from January 2018 to December 2021 (see [here](https://huggingface.co/cardiffnlp/twitter-roberta-base-2021-124m)), and finetuned for sentiment analysis with the TweetEval benchmark. 
+The original roBERTa-base model can be found [here](https://huggingface.co/cardiffnlp/twitter-roberta-base-2021-124m) and the original reference paper is [TweetEval](https://github.com/cardiffnlp/tweeteval). This model is suitable for English. 
+
+- Reference Paper: [TimeLMs paper](https://arxiv.org/abs/2202.03829). 
+- Git Repo: [TimeLMs official repository](https://github.com/cardiffnlp/timelms).
+
+<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
+```

code/inference.py

@@ -0,0 +1,32 @@
+import torch
+
+def predict_fn(data, model_and_tokenizer):
+    # destruct model and tokenizer
+    model, tokenizer = model_and_tokenizer
+    
+    # Tokenize sentences
+    sentences = data.pop("inputs", data)
+    encoded_input = tokenizer(sentences, add_special_tokens=False,return_tensors='pt')
+    input_id_chunks = list(encoded_input['input_ids'][0].split(510))
+    mask_chunks = list(encoded_input['attention_mask'][0].split(510))
+    for i in range(len(input_id_chunks)):
+      input_id_chunks[i]=torch.cat([torch.Tensor([101]),input_id_chunks[i],torch.Tensor([102])])
+      mask_chunks[i] = torch.cat([
+          torch.Tensor([1]), mask_chunks[i], torch.Tensor([1])
+      ])
+      pad_len = 512 - input_id_chunks[i].shape[0]
+      if pad_len > 0:
+          input_id_chunks[i] = torch.cat([input_id_chunks[i],torch.Tensor([0]*pad_len)])
+          mask_chunks[i] = torch.cat([mask_chunks[i],torch.Tensor([0]*pad_len)])
+
+      input_ids = torch.stack(input_id_chunks)
+      attention_masks = torch.stack(mask_chunks)
+
+      input_dict = {
+          'input_ids': input_ids.long(),
+          'attention_mask': attention_masks.int()
+      }
+      output = model(**input_dict)
+      print("inference.py")
+      return output 
+

code/requirements.txt

@@ -0,0 +1 @@
+torch==1.12

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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d24a3e32a88ed1c4e5b789fc6644e2e767500554e954b27dccf52a8e762cbae
+size 501045531

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}}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682358ffb3869b08a144d5e59325534335729720fe64d5f2b3a543f8e5d14a9e
+size 498845224