You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi,
I'm trying to finetune llama 3.1 on chat data. For reference, I'm using data in a format like mentioned in the documentation:
JSONL file with lines like that
[{"content": "hello", "role": "user"}, {"content": "hi nice to meet you", "role": "assistant"}]
[{"content": "how are you", "role": "user"}, {"content": "I am fine", "role": "assistant"}]
[{"content": "What is your name?", "role": "user"}, {"content": "My name is Mary", "role": "assistant"}]
[{"content": "Which is the best programming language?", "role": "user"}, {"content": "Python", "role": "assistant"}]
When running this, you'll get error that key 'text' could not be found.
So the question: is Autotrain able to process such data on it's own?
And what would you recommend to use for the chat_template property with llama and such data format?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi,
I'm trying to finetune llama 3.1 on chat data. For reference, I'm using data in a format like mentioned in the documentation:
JSONL file with lines like that
When running this, you'll get error that key 'text' could not be found.
So the question: is Autotrain able to process such data on it's own?
And what would you recommend to use for the chat_template property with llama and such data format?
Beta Was this translation helpful? Give feedback.
All reactions