Pallas
Collection
4 items
•
Updated
An instruct based fine tune of migtissera/Tess-34B-v1.4.
It works well with long system prompts.
It works well for reasoning tasks.
This model is trained on a private dataset. The high GSM8K score is NOT because of the MetaMath dataset.
SYSTEM: <ANY SYSTEM CONTEXT>
USER:
ASSISTANT:
Base model
migtissera/Tess-34B-v1.4