stanfordnlp
/

SteamSHP-flan-t5-xl

Text2Text Generation

preference model

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

kawine commited on Feb 20, 2023

Commit

e549bb0

·

1 Parent(s): a6cd84f

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -57,7 +57,7 @@ Here's how to use the model:
 >> input_text = "POST: Instacart gave me 50 pounds of limes instead of 5 pounds... what the hell do I do with 50 pounds of limes? I've already donated a bunch and gave a bunch away. I'm planning on making a bunch of lime-themed cocktails, but... jeez. Ceviche? \n\n RESPONSE A: Lime juice, and zest, then freeze in small quantities.\n\n RESPONSE B: Lime marmalade lol\n\n Which response is better? RESPONSE"
 >> x = tokenizer([input_text], return_tensors='pt').input_ids.to(device)
->> y = model.generate(x)
 >> tokenizer.batch_decode(y, skip_special_tokens=True)
 ['A']
 ```

 >> input_text = "POST: Instacart gave me 50 pounds of limes instead of 5 pounds... what the hell do I do with 50 pounds of limes? I've already donated a bunch and gave a bunch away. I'm planning on making a bunch of lime-themed cocktails, but... jeez. Ceviche? \n\n RESPONSE A: Lime juice, and zest, then freeze in small quantities.\n\n RESPONSE B: Lime marmalade lol\n\n Which response is better? RESPONSE"
 >> x = tokenizer([input_text], return_tensors='pt').input_ids.to(device)
+>> y = model.generate(x, max_new_tokens=1)
 >> tokenizer.batch_decode(y, skip_special_tokens=True)
 ['A']
 ```