aliafshar/
gemma3-it-qat-tools:27b

10.3K 5 months ago

Gemma3 instruction-tuned and quantized with tool/functions using a faithful representation of the Google DeepMind recommended tool calling methodology. Runs remarkably well on old GPUs and CPU.

vision tools 1b 4b 12b 27b

5 months ago

e85872e89e88 · 18GB ·

model
gemma3
·
27.4B
·
Q4_0
template
{{- if .System }}<start_of_turn>user {{ .System }}<end_of_turn> {{- end }} {{- if .Tools }}<start_of
params
{ "stop": [ "<end_of_turn>" ], "temperature": 1, "top_k": 64, "top_p": 0

Readme

Gemma3 instruction-tuned and quantized with tool/functions using a faithful representation of the Google DeepMind recommended tool calling methodology. Runs remarkably well on old GPUs and CPU.

References:

See the original Gemma3 information here:

https://ollama.com/library/gemma3