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/components/app/models/utils.ts from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 2.73 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/src/lib/components/app/models/utils.ts
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/tools/ui/src/lib/components/app/models/utils.ts
-
curl -L -o utils.ts https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/src/lib/components/app/models/utils.ts
2.73 kB
| import { ModelModality } from '$lib/enums'; | |
| import type { ModelOption } from '$lib/types/models'; | |
| import { SvelteMap } from 'svelte/reactivity'; | |
| export interface ModelItem { | |
| option: ModelOption; | |
| flatIndex: number; | |
| } | |
| export interface OrgGroup { | |
| orgName: string | null; | |
| items: ModelItem[]; | |
| } | |
| export interface GroupedModelOptions { | |
| loaded: ModelItem[]; | |
| favorites: ModelItem[]; | |
| available: OrgGroup[]; | |
| } | |
| function matchesModality(option: ModelOption, term: string): boolean { | |
| const modalities = option.modalities; | |
| if (!modalities) return false; | |
| switch (term) { | |
| case ModelModality.VISION.toLowerCase(): | |
| return modalities.vision; | |
| case ModelModality.AUDIO.toLowerCase(): | |
| return modalities.audio; | |
| case ModelModality.VIDEO.toLowerCase(): | |
| return modalities.video; | |
| default: | |
| return false; | |
| } | |
| } | |
| export function filterModelOptions(options: ModelOption[], searchTerm: string): ModelOption[] { | |
| const term = searchTerm.trim().toLowerCase(); | |
| if (!term) return options; | |
| return options.filter( | |
| (option) => | |
| option.model.toLowerCase().includes(term) || | |
| option.name?.toLowerCase().includes(term) || | |
| option.aliases?.some((alias: string) => alias.toLowerCase().includes(term)) || | |
| option.tags?.some((tag: string) => tag.toLowerCase().includes(term)) || | |
| matchesModality(option, term) | |
| ); | |
| } | |
| export function groupModelOptions( | |
| filteredOptions: ModelOption[], | |
| favoriteIds: Set<string>, | |
| isModelLoaded: (model: string) => boolean | |
| ): GroupedModelOptions { | |
| // Loaded models | |
| const loaded: ModelItem[] = []; | |
| for (let i = 0; i < filteredOptions.length; i++) { | |
| if (isModelLoaded(filteredOptions[i].model)) { | |
| loaded.push({ flatIndex: i, option: filteredOptions[i] }); | |
| } | |
| } | |
| // Favorites (excluding loaded) | |
| const loadedModelIds = new Set(loaded.map((item) => item.option.model)); | |
| const favorites: ModelItem[] = []; | |
| for (let i = 0; i < filteredOptions.length; i++) { | |
| if ( | |
| favoriteIds.has(filteredOptions[i].model) && | |
| !loadedModelIds.has(filteredOptions[i].model) | |
| ) { | |
| favorites.push({ flatIndex: i, option: filteredOptions[i] }); | |
| } | |
| } | |
| // Available models grouped by org (excluding loaded and favorites) | |
| const available: OrgGroup[] = []; | |
| const orgGroups = new SvelteMap<string, ModelItem[]>(); | |
| for (let i = 0; i < filteredOptions.length; i++) { | |
| const option = filteredOptions[i]; | |
| if (loadedModelIds.has(option.model) || favoriteIds.has(option.model)) continue; | |
| const key = option.parsedId?.orgName ?? ''; | |
| if (!orgGroups.has(key)) orgGroups.set(key, []); | |
| orgGroups.get(key)!.push({ flatIndex: i, option }); | |
| } | |
| for (const [orgName, items] of orgGroups) { | |
| available.push({ items, orgName: orgName || null }); | |
| } | |
| return { available, favorites, loaded }; | |
| } | |