Instructions to use VladHong/llama-cpp-K2-FAST2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use VladHong/llama-cpp-K2-FAST2 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf VladHong/llama-cpp-K2-FAST2 # Run inference directly in the terminal: llama cli -hf VladHong/llama-cpp-K2-FAST2
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf VladHong/llama-cpp-K2-FAST2 # Run inference directly in the terminal: llama cli -hf VladHong/llama-cpp-K2-FAST2
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf VladHong/llama-cpp-K2-FAST2 # Run inference directly in the terminal: ./build/bin/llama cli -hf VladHong/llama-cpp-K2-FAST2
Use Docker
docker model run hf.co/VladHong/llama-cpp-K2-FAST2
- Llama new
- LM Studio
- Jan
- Ollama
How to use VladHong/llama-cpp-K2-FAST2 with Ollama:
ollama run hf.co/VladHong/llama-cpp-K2-FAST2
- Unsloth Desktop
- Docker Model Runner
How to use VladHong/llama-cpp-K2-FAST2 with Docker Model Runner:
docker model run hf.co/VladHong/llama-cpp-K2-FAST2
- Lemonade
How to use VladHong/llama-cpp-K2-FAST2 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull VladHong/llama-cpp-K2-FAST2
Run and chat with the model
lemonade run user.llama-cpp-K2-FAST2-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
File size: 3,987 Bytes
c59fd93 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 | import {
APPLE_DEVICES,
BUILD_CONFIG,
REGEX_PATTERNS,
SPLASH_LINK
} from '../src/lib/constants/pwa.constants';
import { NEWLINE, TAB } from '../src/lib/constants/special-characters.constants';
import { SplashOrientation } from '../src/lib/enums/splash.enums';
import type { SplashDimensions } from '../src/lib/types';
import { existsSync, readdirSync, readFileSync, writeFileSync } from 'node:fs';
import { resolve } from 'path';
import type { Plugin } from 'vite';
let processed = false;
const OUTPUT_DIR = process.env.LLAMA_UI_OUT_DIR ?? BUILD_CONFIG.OUTPUT_DIR;
/**
* Generate iOS splash screen <link> tags from generated apple-splash-*.png files.
* Returns an array of HTML link strings to be injected into the page head.
*/
export function generateSplashScreenLinks(outDir: string): string[] {
const files = readdirSync(outDir).filter((f) => f.match(REGEX_PATTERNS.SPLASH_FILE));
if (files.length === 0) return [];
const dimMap = new Map<string, SplashDimensions>();
for (const [dims, spec] of Object.entries(APPLE_DEVICES)) {
const [w, h] = dims.split('x').map(Number);
// logical-point dimensions
dimMap.set(`${w}x${h}`, { deviceH: spec.height, deviceW: spec.width, dpr: spec.dpr });
dimMap.set(`${h}x${w}`, { deviceH: spec.height, deviceW: spec.width, dpr: spec.dpr });
// pixel dimensions (used by actual generated splash files)
dimMap.set(`${w * spec.dpr}x${h * spec.dpr}`, {
deviceH: spec.height,
deviceW: spec.width,
dpr: spec.dpr
});
dimMap.set(`${h * spec.dpr}x${w * spec.dpr}`, {
deviceH: spec.height,
deviceW: spec.width,
dpr: spec.dpr
});
}
const lightLinks: string[] = [];
const darkLinks: string[] = [];
for (const file of files) {
const match = file.match(REGEX_PATTERNS.SPLASH_FILE);
if (!match) continue;
const orientation = match[1] as SplashOrientation;
const isDark = !!match[2];
const pixelW = parseInt(match[3]);
const pixelH = parseInt(match[4]);
const key = `${pixelW}x${pixelH}`;
const spec = dimMap.get(key);
if (!spec) {
console.warn(`Unknown splash screen dimensions: ${key} (${file})`);
continue;
}
const { deviceH, deviceW, dpr } = spec;
const media = `screen and (device-width: ${deviceW}px) and (device-height: ${deviceH}px) and (-webkit-device-pixel-ratio: ${dpr}) and (orientation: ${orientation})`;
const href = `./${file}`;
if (isDark) {
darkLinks.push(
`${SPLASH_LINK.HTML} media="${media}${SPLASH_LINK.DARK_MEDIA_SUFFIX}" href="${href}">`
);
} else {
lightLinks.push(`${SPLASH_LINK.HTML} media="${media}" href="${href}">`);
}
}
return [...lightLinks, ...darkLinks];
}
export function splashScreenPlugin(): Plugin {
return {
apply: 'build',
closeBundle() {
setTimeout(() => {
try {
if (processed) return;
processed = true;
const outDir = resolve(OUTPUT_DIR);
const indexPath = resolve(outDir, 'index.html');
if (!existsSync(indexPath)) return;
let content = readFileSync(indexPath, 'utf-8');
// Inject iOS splash screen <link> tags into <head>.
// The @vite-pwa/assets-generator generates apple-splash-*.png files;
// this scans them and creates the <link> tags SvelteKit needs.
const splashLinks = generateSplashScreenLinks(outDir);
if (splashLinks.length > 0) {
console.log(`Generated ${splashLinks.length} apple-splash link tags`);
const splashHtml = splashLinks.map((l) => TAB + TAB + l).join(NEWLINE);
content = content.replace(
REGEX_PATTERNS.HEAD_CLOSE,
splashHtml + NEWLINE + TAB + TAB + '</head>'
);
}
// Remove trailing \r from Windows line endings
content = content.replace(/\r/g, '');
content = BUILD_CONFIG.GUIDE_COMMENT + NEWLINE + content;
writeFileSync(indexPath, content, 'utf-8');
console.log('Updated index.html');
} catch (error) {
console.error('Failed to process build output:', error);
}
}, 100);
},
name: 'llamacpp:splash-screen'
};
}
|