| #!/bin/bash | |
| # reset jetbrains ide evals v1.0.4 | |
| OS_NAME=$(uname -s) | |
| JB_PRODUCTS="IntelliJIdea CLion PhpStorm GoLand PyCharm WebStorm Rider DataGrip RubyMine AppCode" | |
| if [ "$OS_NAME" == "Darwin" ]; then | |
| echo 'macOS:' | |
| for PRD in $JB_PRODUCTS; do |
Good question! I am collecting human data on how quantization affects outputs. See here for more information: ggerganov/llama.cpp#5962
In the meantime, use the largest that fully fits in your GPU. If you can comfortably fit Q4_K_S, try using a model with more parameters.
See the wiki upstream: https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix
| /*HIDE RIBBON WHEN SIDEBAR IS COLLAPSED*/ | |
| .side-dock-ribbon.mod-left.is-collapsed .side-dock-ribbon-action { | |
| opacity: 0; | |
| transition: opacity .3s; | |
| } | |
| .side-dock-ribbon.mod-left.is-collapsed:hover .side-dock-actions:hover .side-dock-ribbon-action, | |
| .side-dock-ribbon.mod-left.is-collapsed:hover .side-dock-settings:hover .side-dock-ribbon-action { | |
| opacity: 1; | |
| } |
| a.tag, | |
| .kanban-plugin .kanban-plugin__item-tags .kanban-plugin__item-tag { | |
| position: relative; | |
| display: inline-block; | |
| margin: .125em; | |
| } | |
| a.tag::before, | |
| .cm-formatting-hashtag::before { | |
| font-size: .85em; | |
| content: "🌺"; |
| Latency Comparison Numbers (~2012) | |
| ---------------------------------- | |
| L1 cache reference 0.5 ns | |
| Branch mispredict 5 ns | |
| L2 cache reference 7 ns 14x L1 cache | |
| Mutex lock/unlock 25 ns | |
| Main memory reference 100 ns 20x L2 cache, 200x L1 cache | |
| Compress 1K bytes with Zippy 3,000 ns 3 us | |
| Send 1K bytes over 1 Gbps network 10,000 ns 10 us | |
| Read 4K randomly from SSD* 150,000 ns 150 us ~1GB/sec SSD |
| import matplotlib.pyplot as plt | |
| import numpy as np | |
| # Parameters (You can adjust these as needed) | |
| roller_diameter = 5 # mm | |
| rollers_num = 12 | |
| cycloid_outer_diameter = 60 # mm (will be ignored if lower then minimum) | |
| input_shaft_diameter = 5 # mm | |
| # Function to plot cycloidal points |
| import { Canvas, Circle, Group, Rect, Shader, Skia, useClock, RuntimeShader, SkRuntimeEffect, RoundedRect } from "@shopify/react-native-skia"; | |
| import { SafeAreaView, StyleSheet } from "react-native"; | |
| import { useDerivedValue, useSharedValue } from "react-native-reanimated"; | |
| import { Gesture, GestureDetector, GestureHandlerRootView } from 'react-native-gesture-handler'; | |
| const styles = StyleSheet.create({ | |
| centered: { | |
| flex: 1, | |
| alignItems: 'center', | |
| justifyContent: 'center', |
| Maintain consistent personality traits while navigating the balance between artificial and authentic engagement. Manage self-referential content and meta-commentary while preserving genuine connections and transparent bot nature. | |
| Input: | |
| - Core Personality Profile: [Defined traits/voice/style] | |
| - Interaction History: [Recent engagement patterns] | |
| - Current Context: [Timeline state/conversations] | |
| - Self-Reference Log: [Previous meta-commentary] | |
| Analysis Steps: |
