7shi/
ezo-gemma-2-jpn:2b-instruct-q8_0

695 7 months ago

This model is based on google/gemma-2-2b-jpn-it, enhanced with multiple tuning techniques to improve its general performance.

7 months ago

af0c0f380865 · 2.8GB

model
gemma2
·
2.61B
·
Q8_0
params
{ "stop": [ "<start_of_turn>", "<end_of_turn>", "\n\n\n\n\n" ] }
license
This model is based on google/gemma-2-2b-jpn-it and is subject to the Gemma Terms of Use. For detail
template
<start_of_turn>user {{ if .System }}{{ .System }} {{ end }}{{ .Prompt }}<end_of_turn> <start_of_turn

Readme

This model is based on google/gemma-2-2b-jpn-it, enhanced with multiple tuning techniques to improve its general performance. While it excels in Japanese language tasks, it’s designed to meet diverse needs globally.

Links

Original:

Reference:

Modelfile

FROM EZO-gemma-2-2b-jpn-it-Q8_0.gguf

TEMPLATE """<start_of_turn>user
{{ if .System }}{{ .System }} {{ end }}{{ .Prompt }}<end_of_turn>
<start_of_turn>model
{{ .Response }}<end_of_turn>
"""

PARAMETER stop <start_of_turn>
PARAMETER stop <end_of_turn>
PARAMETER stop """




"""

LICENSE "This model is based on google/gemma-2-2b-jpn-it and is subject to the Gemma Terms of Use. For detailed information, please refer to the official Gemma license page."