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
Download tools/ui/vite.config.ts from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 2.81 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/vite.config.ts
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/tools/ui/vite.config.ts
-
curl -L -o vite.config.ts https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/vite.config.ts
2.81 kB
| import { buildInfoPlugin } from './scripts/vite-plugin-build-info'; | |
| import { nerdamerPlugin } from './scripts/vite-plugin-nerdamer'; | |
| import { relativizeBasePlugin } from './scripts/vite-plugin-relativize-base'; | |
| import { splashScreenPlugin } from './scripts/vite-plugin-splash-screen'; | |
| import { SVELTEKIT_PWA_OPTIONS } from './src/lib/constants/pwa.constants'; | |
| import { storybookTest } from '@storybook/addon-vitest/vitest-plugin'; | |
| import { sveltekit } from '@sveltejs/kit/vite'; | |
| import tailwindcss from '@tailwindcss/vite'; | |
| import { SvelteKitPWA } from '@vite-pwa/sveltekit'; | |
| import { playwright } from '@vitest/browser-playwright'; | |
| import { dirname, resolve } from 'path'; | |
| import { fileURLToPath } from 'url'; | |
| import { defineConfig, loadEnv, searchForWorkspaceRoot } from 'vite'; | |
| const __dirname = dirname(fileURLToPath(import.meta.url)); | |
| // eslint-disable-next-line @typescript-eslint/no-explicit-any | |
| const browserBaseConfig: any = { | |
| enabled: true, | |
| instances: [{ browser: 'chromium' }], | |
| provider: playwright({ | |
| launchOptions: { | |
| args: ['--no-sandbox'] | |
| } | |
| }) | |
| }; | |
| export default defineConfig(({ mode }) => { | |
| const env = loadEnv(mode, process.cwd(), 'VITE_PUBLIC_'); | |
| const SERVER_ORIGIN = env.VITE_PUBLIC_SERVER_ORIGIN || 'http://localhost:8080'; | |
| return { | |
| build: { | |
| assetsInlineLimit: 32000, | |
| chunkSizeWarningLimit: 3072, | |
| minify: true | |
| }, | |
| plugins: [ | |
| tailwindcss(), | |
| sveltekit(), | |
| SvelteKitPWA(SVELTEKIT_PWA_OPTIONS), | |
| splashScreenPlugin(), | |
| buildInfoPlugin(), | |
| nerdamerPlugin(), | |
| relativizeBasePlugin() | |
| ], | |
| resolve: { | |
| alias: { | |
| 'katex-fonts': resolve('node_modules/katex/dist/fonts') | |
| } | |
| }, | |
| server: { | |
| fs: { | |
| allow: [searchForWorkspaceRoot(process.cwd()), resolve(__dirname, 'tests')] | |
| }, | |
| headers: { | |
| 'Cross-Origin-Embedder-Policy': 'require-corp', | |
| 'Cross-Origin-Opener-Policy': 'same-origin' | |
| }, | |
| proxy: { | |
| '/cors-proxy': SERVER_ORIGIN, | |
| '/models': SERVER_ORIGIN, | |
| '/props': SERVER_ORIGIN, | |
| '/slots': SERVER_ORIGIN, | |
| '/tools': SERVER_ORIGIN, | |
| '/v1': SERVER_ORIGIN | |
| } | |
| }, | |
| test: { | |
| projects: [ | |
| { | |
| extends: './vite.config.ts', | |
| test: { | |
| browser: browserBaseConfig, | |
| include: ['tests/client/**/*.svelte.{test,spec}.{js,ts}'], | |
| name: 'client', | |
| setupFiles: ['./vitest-setup-client.ts'] | |
| } | |
| }, | |
| { | |
| extends: './vite.config.ts', | |
| test: { | |
| environment: 'node', | |
| include: ['tests/unit/**/*.{test,spec}.{js,ts}'], | |
| name: 'unit' | |
| } | |
| }, | |
| { | |
| extends: './vite.config.ts', | |
| plugins: [ | |
| storybookTest({ | |
| storybookScript: 'pnpm run storybook --no-open' | |
| }) | |
| ], | |
| test: { | |
| browser: { ...browserBaseConfig, instances: [{ browser: 'chromium', headless: true }] }, | |
| name: 'ui' | |
| } | |
| } | |
| ] | |
| } | |
| }; | |
| }); | |