Update README.md

README.md

@@ -52,6 +52,24 @@ LongForm-**T5-XL**: https://huggingface.co/akoksal/LongForm-T5-XL
 
 LongForm-**OPT-2.7B**: https://huggingface.co/akoksal/LongForm-OPT-2.7B
 
+## How to Load
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+model = AutoModelForCausalLM.from_pretrained("akoksal/LongForm-OPT-6.7B")
+tokenizer = AutoTokenizer.from_pretrained("akoksal/LongForm-OPT-6.7B")
+
+instruction = "Write an essay about meditation. [EOI]"
+torch.manual_seed(42)
+input_ids = tokenizer(instruction, return_tensors="pt").input_ids
+target_ids = model.generate(input_ids, do_sample=True, max_new_tokens=50, top_p=0.9)
+tokenizer.decode(target_ids[0])
+# Output:
+# > </s>Write an essay about meditation. [EOI]Meditation is a way to quiet the\
+# mind, focus on the present, and achieve a calm and serene state of mind.\
+# In today's society, people are constantly running from one thing to the next.\
+# In order to maintain good mental health,
+```
 
 ## Evaluation
 We provide in-depth evaluation of LongForm models and baselines in the paper. We present the METEOR scores of models in out-of-domain datasets. In all tasks, Recipe Generation (RGen), long-form question answering (ELI5), short story generation (WritingPrompts/WP), LongForm models outperform prior instruction-tuned models.