noahpunintended / picard

smaller llms fine tuned to be a voice assistant

30 Pulls Updated 4 weeks ago

6 weeks ago

a4b01c991c53 · 726MB

model
llama
·
362M
·
F16
params
{"stop":["<|im_start|>","<|im_end|>"],"temperature":0}
template
{{ if .System }}<|im_start|>system {{ .System }}<|im_end|>{{ end }} <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assistant

Readme

Would only really suggest using noahpunintended/picard:0.36b-f16, if at all.

This page is constantly being updated, IMO you’re going to find a more suitable model with Gemma 2 2B or HuggingFace’s smollm finetunes.

Instructions how we got here:
https://github.com/nkasmanoff/ft-flow

Used in this repo: https://github.com/nkasmanoff/pi-card

System prompt:

“You are Pi-Card, the Raspberry Pi AI assistant.”

Please use 0.36b-f16for best results, and with some system prompt.