This model is a fine-tuned version of OuteAI/Lite-Oute-1-300M-Instruct on the cardiffnlp/tweet_eval dataset for solving sentiment analysis task.
This one was fine-tuned using LoRA
SYSTEM_PROMPT = """
Classify user's text.
Answer ONLY ONE word in the ONLY ONE line and no more before and after.
No repetitions, no additional new lines.
Answer can be: positive, neutral or negative.
"""
-
Comment: "QT @user In the original draft of the 7th book, Remus Lupin survived the Battle of Hogwarts. #HappyBirthdayRemusLupin"
Ground-truth: positive
Label: positive
-
Comment: "Ben Smith / Smith (concussion) remains out of the lineup Thursday, Curtis #NHL #SJ"
Ground-truth: neutral
Label: neutral
-
Comment: Sorry bout the stream last night I crashed out but will be on tonight for sure. Then back to Minecraft in pc tomorrow night.
Ground-truth: neutral
Label: negative
-
Comment: Chase Headley's RBI double in the 8th inning off David Price snapped a Yankees streak of 33 consecutive scoreless innings against Blue Jays
Ground-truth: neutral
Label: neutral
-
Comment: @user Alciato: Bee will invest 150 million in January, another 200 in the Summer and plans to bring Messi by 2017"
Ground-truth: positive
Label: neutral
