Update README.md

README.md

@@ -31,6 +31,7 @@ Now, with Instruct GPT-J, you can ask things in natural language "like a human":
 ```text
 Correct spelling and grammar from the following text.
 I do not wan to go
+
 ```
 
 Which returns the following:
@@ -51,7 +52,7 @@ import torch
 
 generator = pipeline(model="nlpcloud/instruct-gpt-j", torch_dtype=torch.float16, device=0)
 
-prompt = "Correct spelling and grammar from the following text.\nI do not wan to go"
+prompt = "Correct spelling and grammar from the following text.\nI do not wan to go\n"
 
 print(generator(prompt))
 ```
@@ -65,7 +66,7 @@ import torch
 tokenizer = AutoTokenizer.from_pretrained('nlpcloud/instruct-gpt-j')
 generator = AutoModelForCausalLM.from_pretrained("nlpcloud/instruct-gpt-j",torch_dtype=torch.float16).cuda()
 
-prompt = "Correct spelling and grammar from the following text.\nI do not wan to go"
+prompt = "Correct spelling and grammar from the following text.\nI do not wan to go\n"
 
 inputs = tokenizer(prompt, return_tensors='pt')
 outputs = generator.generate(inputs.input_ids.cuda())
@@ -73,6 +74,22 @@ outputs = generator.generate(inputs.input_ids.cuda())
 print(tokenizer.decode(outputs[0]))
 ```
 
+## Special Note About Input Format
+
+Due to the way this model was fine-tuned, you should always use new lines at the end of your instructions.
+
+For example the following instruction might not always work:
+
+```text
+Correct spelling and grammar from the following text.\nI do not wan to go
+```
+
+But this one would:
+
+```text
+Correct spelling and grammar from the following text.\nI do not wan to go\n
+```
+
 ## Hardware Requirements
 
 This model is an fp16 version of our fine-tuned model, which works very well on a GPU with 16GB of VRAM like an NVIDIA Tesla T4.