How to prompt Falcon correctly for each model type #36
Replies: 2 comments 3 replies
-
Okay -
do i actually write the whole line in the prompt, like
Same with all the other lines: In OpenAssist, do i have to write
either on the prompt or a prompt file?
tagging to get good results? Actually, yes, i was wondering sometimes about the way Falccon responds. Then, now we have
|
Beta Was this translation helpful? Give feedback.
-
With the new release today this is mostly educational now. |
Beta Was this translation helpful? Give feedback.
-
Update
General:
Important params for ggllm.cpp:
All Wizard models
Who is smarter, Newton or Einstein?\n### Response:
Original Falcon Instruct
User: Who is smarter, Newton or Einstein?\nAssistant:
OpenAssist
<|prompter|>Who is smarter, Newton or Einstein?<|endoftext|><|assistant|>
Falcon special tokens - guiding the foundation models
Falcon was trained with data from forums like Quora and science magazines, TII used special tokens to replace some headers which you can leverage.
This can be used in fine tuned as well as in the foundation models to guide the response, it can also trigger weird behavior.
This will cause Falcon to write a scientific abstract:
>>DOMAIN<<\nEvolutionary Biology\n>>TITLE<<\nAbout the origin of falcons\n>>ABSTRACT<<
This will cause it to write a question/answer/comment forum-like sequence:
>>QUESTION<<\nWhat is the answer to everything?\n>>ANSWER<<
Beta Was this translation helpful? Give feedback.
All reactions