yazon

@yazon

I like Computers and South Park. I'm also fascinated by topics like Neuroscience, EEG, BCI, Automation, ML/DL/AI, Human Consciousness & more.

Joined April 2025

Projects

Conspired to be claude sys prompt

PRESET

146

Updated on August 16

System prompt to show the model how to write tools with lmstudio-js

PRESET

141

Updated on August 16
Public

PRESET

123

Updated on August 25

PRESET

122

Updated on July 28
Public

PRESET

128

Updated on July 28
Public

PRESET

129

Updated on August 29

PRESET

122

Updated on July 22
Public

PRESET

113

Updated on July 17
Public

PRESET

128

Updated on July 17

PRESET

124

Updated on July 17

PRESET

116

Updated on July 17

PRESET

138

Updated on July 16

PRESET

140

Updated on July 16
Public

PRESET

119

Updated 20 days ago
Public

According to the Gemma team, the optimal config for inference is temperature = 1.0, top_k = 64, top_p = 0.95, min_p = 0.0 (optional 0.01)

PRESET

123

Updated on July 11
Public

PRESET

137

1

Updated on May 31

PRESET

131

Updated on May 31

With official sampling parameters. Note: According to Nvidia the non-thinking mode should be a greedy sampling.

PRESET

128

Updated on May 23

With the official sampling parameters.

PRESET

127

Updated on July 16
Public

The default settings for Qwen-3 models according to Qwen-Team. Default means that reasoning is automatically enabled, unless you end your user message with `/no_think`. For example if you just want to smalltalk then do this: ``` Hello there, how ar...

PRESET

135

1

Updated on April 30

The non-reasoning settings with the parameters as recommended officially by Qwen-Team. Note that I've set repetition penalty to 1.1 - feel free to change this parameter and experiment with it, but the other parameters should remain unchanged if you...

PRESET

140

1

Updated on April 30