Evaluation of some questions don't seem to be consistant with instructions
#4
by
Baptbe
- opened
Example:
Question #1
No specifics on which model to use.
If you leave the HfApiModel() to default it throws a mistake, if you use a Llama model it throws a mistake.
Despite no specific instructions, it is expected to use the Qwen default model and hardcode it.
Suggestions:
- give more specific instructions and assume a specific model should be used and declared
- let go with any model the user would like to use
