Update README.md

README.md

@@ -10,45 +10,48 @@ model-index:
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
-
-# roberta-large-fiie
-
-This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 8
-- eval_batch_size: 4
-- seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 32
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 1.0
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.35.2
-- Pytorch 2.0.0+cu117
-- Datasets 2.15.0
-- Tokenizers 0.15.0
+```python
+from transformers import AutoModelForTokenClassification, AutoTokenizer
+import torch
+
+device = torch.device("cuda:0")
+path = f"KomeijiForce/roberta-large-metaie"
+tokenizer = AutoTokenizer.from_pretrained(path)
+tagger = AutoModelForTokenClassification.from_pretrained(path).to(device)
+
+def find_sequences(lst):
+    sequences = []
+    i = 0
+    while i < len(lst):
+        if lst[i] == 0:
+            start = i
+            end = i
+            i += 1
+            while i < len(lst) and lst[i] == 1:
+                end = i
+                i += 1
+            sequences.append((start, end+1))
+        else:
+            i += 1
+    return sequences
+
+def is_sublst(lst1, lst2):
+    for idx in range(len(lst1)-len(lst2)+1):
+        if lst1[idx:idx+len(lst2)] == lst2:
+            return True
+    return False
+
+words = ["John", "Smith", "loves", "his", "hometown", ",", "Los", "Angeles", "."]
+
+for prefix in ["Person", "Location", "John Smith births in", "Positive opinion"]:
+
+    sentence = " ".join([prefix, ":"]+words)
+
+    inputs = tokenizer(sentence, return_tensors="pt").to(device)
+    tag_predictions = tagger(**inputs).logits[0].argmax(-1)
+
+    predictions = [tokenizer.decode(inputs.input_ids[0, seq[0]:seq[1]]).strip() for seq in find_sequences(tag_predictions)]
+    predictions = [prediction for prediction in predictions if is_sublst(words, prediction.split())]
+    
+    print(prefix, predictions)
+```