Update README.md

README.md

@@ -13,10 +13,12 @@ It is the main model from the paper (see **"T5-11B w. ANLI + TrueTeacher full"**
 
 The input format for the model is: "premise: GROUNDING_DOCUMENT hypothesis: HYPOTHESIS_SUMMARY".
 
+To accomodate the input length of common summarization datasets we recommend setting **max_length** to **2048**.
+
 The model predicts a binary label ('1' - Factualy Consistent, '0' - Factualy Inconsistent).
 
 
-## Usage example:
+## Usage example - classifiaction:
 ```python
 from transformers import T5ForConditionalGeneration
 from transformers import T5Tokenizer
@@ -28,7 +30,11 @@ model = T5ForConditionalGeneration.from_pretrained(model_path)
 premise = 'the sun is shining'
 for hypothesis, expected in [('the sun is out in the sky', '1'), 
                              ('the cat is shiny', '0')]:
-  input_ids = tokenizer(f'premise: {premise} hypothesis: {hypothesis}', return_tensors='pt').input_ids
+  input_ids = tokenizer(
+      f'premise: {premise} hypothesis: {hypothesis}',
+      return_tensors='pt',
+      truncation=True,
+      max_length=2048).input_ids
   outputs = model.generate(input_ids)
   result = tokenizer.decode(outputs[0], skip_special_tokens=True)
   print(f'premise: {premise}')
@@ -36,6 +42,35 @@ for hypothesis, expected in [('the sun is out in the sky', '1'),
   print(f'result: {result} (expected: {expected})\n')
 ```
 
+## Usage example - scoring:
+```python
+from transformers import T5ForConditionalGeneration
+from transformers import T5Tokenizer
+import torch
+
+model_path = 'google/t5_11b_trueteacher_and_anli'
+tokenizer = T5Tokenizer.from_pretrained(model_path)
+model = T5ForConditionalGeneration.from_pretrained(model_path)
+
+premise = 'the sun is shining'
+for hypothesis, expected in [('the sun is out in the sky', '>> 0.5'), 
+                             ('the cat is shiny', '<< 0.5')]:
+  input_ids = tokenizer(
+      f'premise: {premise} hypothesis: {hypothesis}',
+      return_tensors='pt',
+      truncation=True,
+      max_length=2048).input_ids
+  decoder_input_ids = torch.tensor([[tokenizer.pad_token_id]])
+  outputs = model(input_ids=input_ids, decoder_input_ids=decoder_input_ids)
+  logits = outputs.logits
+  probs = torch.softmax(logits[0], dim=-1)
+  one_token_id = tokenizer('1').input_ids[0]
+  entailment_prob = probs[0, one_token_id].item()
+  print(f'premise: {premise}')
+  print(f'hypothesis: {hypothesis}')
+  print(f'score: {entailment_prob:.3f} (expected: {expected})\n')
+```
+
 ## Citation
 
 If you use this model for a research publication, please cite the TrueTeacher paper (using the bibtex entry below) and the dataset papers mentioned above.