grammarly
/

coedit-xl-composite

Text2Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

machineteacher commited on May 12, 2023

Commit

e3e7026

•

1 Parent(s): df45c2c

Update README.md

Files changed (1) hide show

README.md +6 -3

README.md CHANGED Viewed

@@ -62,13 +62,16 @@ Given an edit instruction and an original text, our model can generate the edite
 ![task_specs](https://huggingface.co/grammarly/coedit-xl/resolve/main/Screen%20Shot%202023-05-12%20at%203.36.37%20PM.png)
 ## Usage
 ```python
 from transformers import AutoTokenizer, T5ForConditionalGeneration
-tokenizer = AutoTokenizer.from_pretrained("grammarly/coedit-large")
-model = T5ForConditionalGeneration.from_pretrained("grammarly/coedit-large")
-input_text = 'Fix grammatical errors in this sentence: New kinds of vehicles will be invented with new technology than today.'
 input_ids = tokenizer(input_text, return_tensors="pt").input_ids
 outputs = model.generate(input_ids, max_length=256)
 edited_text = tokenizer.decode(outputs[0], skip_special_tokens=True)[0]

 ![task_specs](https://huggingface.co/grammarly/coedit-xl/resolve/main/Screen%20Shot%202023-05-12%20at%203.36.37%20PM.png)
+This model can also perform edits on composite instructions, as shown below:
+![composite task_specs](https://huggingface.co/grammarly/coedit-xl-composite/resolve/main/composite_examples.png)
 ## Usage
 ```python
 from transformers import AutoTokenizer, T5ForConditionalGeneration
+tokenizer = AutoTokenizer.from_pretrained("grammarly/coedit-xl-composite")
+model = T5ForConditionalGeneration.from_pretrained("grammarly/coedit-xl-composite")
+input_text = 'Fix grammatical errors in this sentence and make it simpler: New kinds of vehicles will be invented with new technology than today.'
 input_ids = tokenizer(input_text, return_tensors="pt").input_ids
 outputs = model.generate(input_ids, max_length=256)
 edited_text = tokenizer.decode(outputs[0], skip_special_tokens=True)[0]