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/tests/unit/stream-discovery.test.ts from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 3.56 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/tests/unit/stream-discovery.test.ts
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/tools/ui/tests/unit/stream-discovery.test.ts
-
curl -L -o stream-discovery.test.ts https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/tests/unit/stream-discovery.test.ts
3.56 kB
| import { ChatService } from '$lib/services/chat.service'; | |
| import type { ApiStreamSession } from '$lib/types'; | |
| import { describe, expect, it } from 'vitest'; | |
| function makeSession(overrides: Partial<ApiStreamSession>): ApiStreamSession { | |
| return { | |
| completed_at: 0, | |
| conversation_id: 'conv', | |
| is_done: true, | |
| started_at: 0, | |
| total_bytes: 0, | |
| ...overrides | |
| }; | |
| } | |
| describe('selectActiveStream', () => { | |
| it('returns null on empty input', () => { | |
| expect(ChatService.selectActiveStream([])).toBeNull(); | |
| }); | |
| it('returns null on null or undefined input', () => { | |
| expect(ChatService.selectActiveStream(null)).toBeNull(); | |
| expect(ChatService.selectActiveStream(undefined)).toBeNull(); | |
| }); | |
| it('returns the single session when it is running', () => { | |
| const s = makeSession({ conversation_id: 'only', is_done: false, started_at: 42 }); | |
| expect(ChatService.selectActiveStream([s])).toBe(s); | |
| }); | |
| it('returns null when the single session is finalized', () => { | |
| const s = makeSession({ conversation_id: 'only', is_done: true, started_at: 42 }); | |
| expect(ChatService.selectActiveStream([s])).toBeNull(); | |
| }); | |
| it('prefers a still running session over a finalized one regardless of started_at', () => { | |
| const finalized = makeSession({ conversation_id: 'old', is_done: true, started_at: 1000 }); | |
| const running = makeSession({ conversation_id: 'new', is_done: false, started_at: 10 }); | |
| expect(ChatService.selectActiveStream([finalized, running])?.conversation_id).toBe('new'); | |
| expect(ChatService.selectActiveStream([running, finalized])?.conversation_id).toBe('new'); | |
| }); | |
| it('among running sessions, picks the most recently started one', () => { | |
| const a = makeSession({ conversation_id: 'a', is_done: false, started_at: 100 }); | |
| const b = makeSession({ conversation_id: 'b', is_done: false, started_at: 200 }); | |
| const c = makeSession({ conversation_id: 'c', is_done: false, started_at: 150 }); | |
| expect(ChatService.selectActiveStream([a, b, c])?.conversation_id).toBe('b'); | |
| expect(ChatService.selectActiveStream([c, a, b])?.conversation_id).toBe('b'); | |
| }); | |
| it('returns null when all sessions are finalized, the DB already holds the content', () => { | |
| const a = makeSession({ conversation_id: 'a', is_done: true, started_at: 10 }); | |
| const b = makeSession({ conversation_id: 'b', is_done: true, started_at: 30 }); | |
| const c = makeSession({ conversation_id: 'c', is_done: true, started_at: 20 }); | |
| expect(ChatService.selectActiveStream([a, b, c])).toBeNull(); | |
| }); | |
| it('keeps the first match on ties when both are running with identical started_at', () => { | |
| // reduce visits left to right, the initial accumulator stays unless a strictly greater value appears | |
| const a = makeSession({ conversation_id: 'first', is_done: false, started_at: 50 }); | |
| const b = makeSession({ conversation_id: 'second', is_done: false, started_at: 50 }); | |
| expect(ChatService.selectActiveStream([a, b])?.conversation_id).toBe('first'); | |
| }); | |
| it('handles a typical realistic mix: two finalized old, one freshly running, one freshly finalized', () => { | |
| const old1 = makeSession({ conversation_id: 'old1', is_done: true, started_at: 100 }); | |
| const old2 = makeSession({ conversation_id: 'old2', is_done: true, started_at: 200 }); | |
| const freshFin = makeSession({ conversation_id: 'freshFin', is_done: true, started_at: 500 }); | |
| const running = makeSession({ conversation_id: 'running', is_done: false, started_at: 400 }); | |
| expect(ChatService.selectActiveStream([old1, old2, freshFin, running])?.conversation_id).toBe( | |
| 'running' | |
| ); | |
| }); | |
| }); | |