Mistral Syndicate is in no way a state-of-the-art model, rather it is a fine-tuning experiment to explore
the training dynamics specific to large language models. The dataset used in finetuning was generated via
a "syndicate" of other open language models both of similar parameter size and larger. Each model would generate a
response for a given instruction, and the group would vote on which model's response was best.
The instruction inputs used for the output label synthesis were a curated subset of VMWare/open-instruct
with additional instructions synthesized from scratch.
Prompt template
With context
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
### Input:
### Response:
Without context
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
### Response:
