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/sse.test.ts from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 2.43 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/tests/unit/sse.test.ts
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/tools/ui/tests/unit/sse.test.ts
-
curl -L -o sse.test.ts https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/tests/unit/sse.test.ts
2.43 kB
| import { parseSseJsonStream } from '$lib/utils/sse'; | |
| import { describe, expect, it } from 'vitest'; | |
| function makeSseResponse(events: string[]): Response { | |
| const body = events.join('\n\n') + '\n\n'; | |
| return new Response(body, { | |
| headers: { 'content-type': 'text/event-stream' }, | |
| status: 200 | |
| }); | |
| } | |
| describe('parseSseJsonStream', () => { | |
| it('yields parsed data for each record', async () => { | |
| const response = makeSseResponse(['data: {"chunk": "a"}', 'data: {"chunk": "b"}']); | |
| const collected: unknown[] = []; | |
| for await (const ev of parseSseJsonStream(response)) { | |
| collected.push(ev.data); | |
| } | |
| expect(collected).toEqual([{ chunk: 'a' }, { chunk: 'b' }]); | |
| }); | |
| it('stops on [DONE] sentinel', async () => { | |
| const response = makeSseResponse([ | |
| 'data: {"chunk": "a"}', | |
| 'data: [DONE]', | |
| 'data: {"chunk": "after-done"}' | |
| ]); | |
| const collected: unknown[] = []; | |
| for await (const ev of parseSseJsonStream(response)) { | |
| collected.push(ev.data); | |
| } | |
| expect(collected).toEqual([{ chunk: 'a' }]); | |
| }); | |
| it('skips malformed JSON records', async () => { | |
| const response = makeSseResponse([ | |
| 'data: {"chunk": "ok"}', | |
| 'data: {not-json}', | |
| 'data: {"chunk": "also-ok"}' | |
| ]); | |
| const collected: unknown[] = []; | |
| for await (const ev of parseSseJsonStream(response)) { | |
| collected.push(ev.data); | |
| } | |
| expect(collected).toEqual([{ chunk: 'ok' }, { chunk: 'also-ok' }]); | |
| }); | |
| it('handles records split across multiple chunks (partial last line)', async () => { | |
| const full = 'data: {"chunk": "x"}\n\ndata: {"chunk": "y"}\n\n'; | |
| const stream = new ReadableStream<Uint8Array>({ | |
| start(controller) { | |
| const enc = new TextEncoder(); | |
| controller.enqueue(enc.encode(full.slice(0, full.length / 2))); | |
| controller.enqueue(enc.encode(full.slice(full.length / 2))); | |
| controller.close(); | |
| } | |
| }); | |
| const response = new Response(stream, { | |
| headers: { 'content-type': 'text/event-stream' }, | |
| status: 200 | |
| }); | |
| const collected: unknown[] = []; | |
| for await (const ev of parseSseJsonStream(response)) { | |
| collected.push(ev.data); | |
| } | |
| expect(collected).toEqual([{ chunk: 'x' }, { chunk: 'y' }]); | |
| }); | |
| it('returns immediately if response has no body', async () => { | |
| const response = new Response(null, { status: 200 }); | |
| const collected: unknown[] = []; | |
| for await (const ev of parseSseJsonStream(response)) { | |
| collected.push(ev.data); | |
| } | |
| expect(collected).toEqual([]); | |
| }); | |
| }); | |