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
I'm doing local inference of my custom model, and the dataset by which I trained my llm has a different chat template (chatml). Hence while creating completion, I ought to use that format, but it gives error of messages has no key "role", while my dataset doesn't have "role" key-value, here's an example: { "id": "02", "conversation": [ { "from": "gpt", "value": "Hi, how can I help you today? Please describe the codebase you want to deploy." }, { "from": "human", "value": "I need help deploying a Node.js app. It's built with Express.js and uses MongoDB." } ]}
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
-
I'm doing local inference of my custom model, and the dataset by which I trained my llm has a different chat template (chatml). Hence while creating completion, I ought to use that format, but it gives error of
messages has no key "role"
, while my dataset doesn't have "role" key-value, here's an example:{ "id": "02", "conversation": [ { "from": "gpt", "value": "Hi, how can I help you today? Please describe the codebase you want to deploy." }, { "from": "human", "value": "I need help deploying a Node.js app. It's built with Express.js and uses MongoDB." } ]}
Beta Was this translation helpful? Give feedback.
All reactions