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/constants/mcp.constants.ts from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 2.8 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/src/lib/constants/mcp.constants.ts
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/tools/ui/src/lib/constants/mcp.constants.ts
-
curl -L -o mcp.constants.ts https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/src/lib/constants/mcp.constants.ts
2.8 kB
| import { Globe, Radio, Zap } from '@lucide/svelte'; | |
| import { MCPTransportType } from '$lib/enums'; | |
| import { MimeTypeImage } from '$lib/enums/files.enums'; | |
| import type { ClientCapabilities, Implementation } from '$lib/types'; | |
| import type { Component } from 'svelte'; | |
| export const DEFAULT_CLIENT_VERSION = '1.0.0'; | |
| export const MCP_CLIENT_NAME = 'llama-ui-mcp'; | |
| export const DEFAULT_IMAGE_MIME_TYPE = MimeTypeImage.PNG; | |
| /** MIME types considered safe for rendering MCP server icons */ | |
| export const MCP_ALLOWED_ICON_MIME_TYPES = new Set([ | |
| MimeTypeImage.PNG, | |
| MimeTypeImage.JPEG, | |
| MimeTypeImage.JPG, | |
| MimeTypeImage.SVG, | |
| MimeTypeImage.WEBP, | |
| MimeTypeImage.ICO, | |
| MimeTypeImage.ICO_MICROSOFT | |
| ]); | |
| /** | |
| * MCP specification version this client targets. | |
| * Update when the upstream MCP spec introduces a new stable version: | |
| * https://spec.modelcontextprotocol.io/ | |
| */ | |
| export const MCP_PROTOCOL_VERSION = '2025-06-18'; | |
| export const DEFAULT_MCP_CONFIG = { | |
| capabilities: { tools: { listChanged: true } } as ClientCapabilities, | |
| clientInfo: { name: MCP_CLIENT_NAME, version: DEFAULT_CLIENT_VERSION } as Implementation, | |
| connectionTimeoutMs: 10_000, // 10 seconds for connection establishment | |
| protocolVersion: MCP_PROTOCOL_VERSION, | |
| requestTimeoutSeconds: 300 // 5 minutes for long-running tools | |
| } as const; | |
| export const MCP_SERVER_ID_PREFIX = 'LlamaUI-MCP-Server'; | |
| /** Backoff policy for reconnecting to a dropped MCP server. */ | |
| export const MCP_RECONNECT = { | |
| /** Per-attempt timeout for a single reconnection attempt before giving up and backing off. */ | |
| ATTEMPT_TIMEOUT_MS: 15_000, | |
| BACKOFF_MULTIPLIER: 2, | |
| INITIAL_DELAY: 1000, | |
| MAX_DELAY: 30000 | |
| }; | |
| /** Maximum number of MCP server avatars to display in the chat form */ | |
| export const MAX_DISPLAYED_MCP_AVATARS = 4; | |
| /** Expected count when two theme-less icons represent a light/dark pair */ | |
| export const EXPECTED_THEMED_ICON_PAIR_COUNT = 2; | |
| /** CORS proxy connection settings */ | |
| export const CORS_PROXY = { | |
| /** Header prefix for headers that should be forwarded by the CORS proxy */ | |
| HEADER_PREFIX: 'x-llama-server-proxy-header-', | |
| /** CORS proxy URL query parameter name */ | |
| URL_PARAM: 'url' | |
| } as const; | |
| /** Standard SSE endpoint path indicators */ | |
| export const MCP_SSE = { | |
| ENDPOINT: '/sse', | |
| ENDPOINT_QUERY: '/sse?', | |
| ENDPOINT_SLASH: '/sse/' | |
| } as const; | |
| /** Human-readable labels for MCP transport types */ | |
| export const MCP_TRANSPORT_LABELS: Record<MCPTransportType, string> = { | |
| [MCPTransportType.SSE]: 'SSE', | |
| [MCPTransportType.STREAMABLE_HTTP]: 'HTTP', | |
| [MCPTransportType.WEBSOCKET]: 'WebSocket' | |
| }; | |
| /** Icon components for MCP transport types */ | |
| export const MCP_TRANSPORT_ICONS: Record<MCPTransportType, Component> = { | |
| [MCPTransportType.SSE]: Radio, | |
| [MCPTransportType.STREAMABLE_HTTP]: Globe, | |
| [MCPTransportType.WEBSOCKET]: Zap | |
| }; | |