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/src/lib/services/sandbox-harness.ts from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 1.92 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/src/lib/services/sandbox-harness.ts
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/tools/ui/src/lib/services/sandbox-harness.ts
-
curl -L -o sandbox-harness.ts https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/src/lib/services/sandbox-harness.ts
1.92 kB
| /** | |
| * Sandbox harness - builds the srcdoc document for the sandboxed iframe | |
| * | |
| * Produces the HTML/CSP/worker shim that runs untrusted model code in an | |
| * opaque origin. Consumed by sandbox.service. | |
| */ | |
| import WORKER_SHIM from './sandbox-worker.js?raw'; | |
| import { NEWLINE } from '$lib/constants'; | |
| /** | |
| * CSP for the harness document, inherited by the blob worker. connect-src | |
| * falls back to default-src, removing network egress for model and vendored | |
| * code. 'unsafe-eval' is required by the worker's AsyncFunction constructor, | |
| * 'unsafe-inline' by the inline script below, worker-src by the blob worker. | |
| */ | |
| const HARNESS_CSP = `default-src 'none'; script-src 'unsafe-inline' 'unsafe-eval'; worker-src blob:`; | |
| /** | |
| * Harness loaded as srcdoc into a sandboxed iframe (allow-scripts only). | |
| * The opaque origin is the security boundary: no access to the app origin, | |
| * its storage or its API. The harness spawns a worker so model code never | |
| * runs on a main thread, which makes the parent timeout enforceable by | |
| * removing the iframe. The prelude runs in the worker before the shim, | |
| * exposing globals such as `nerdamer` to model code. | |
| */ | |
| export function buildSandboxHarness(preludeJs: string): string { | |
| return `<!doctype html><meta http-equiv="Content-Security-Policy" content="${HARNESS_CSP}"><script> | |
| const SHIM = ${JSON.stringify(preludeJs + NEWLINE + WORKER_SHIM)}; | |
| addEventListener('message', (event) => { | |
| const respond = (payload) => parent.postMessage(payload, '*'); | |
| let worker; | |
| try { | |
| worker = new Worker(URL.createObjectURL(new Blob([SHIM], { type: 'text/javascript' }))); | |
| } catch (err) { | |
| respond({ logs: [], result: null, error: 'Worker creation failed: ' + err }); | |
| return; | |
| } | |
| worker.onmessage = (msg) => respond(msg.data); | |
| worker.onerror = (err) => respond({ logs: [], result: null, error: String(err.message || err) }); | |
| worker.postMessage({ code: event.data.code }); | |
| }); | |
| </script>`; | |
| } | |