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/read-media.ts from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 2.14 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/src/lib/constants/read-media.ts
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/tools/ui/src/lib/constants/read-media.ts
-
curl -L -o read-media.ts https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/src/lib/constants/read-media.ts
2.14 kB
| import { | |
| BuiltInTool, | |
| JsonSchemaType, | |
| MimeTypeAudio, | |
| MimeTypeImage, | |
| ToolCallType | |
| } from '$lib/enums'; | |
| import type { OpenAIToolDefinition } from '$lib/types'; | |
| export const READ_MEDIA_TOOL_NAME = BuiltInTool.BROWSER_READ_MEDIA; | |
| // header lines of the tool result, parsed back by the read_media renderer | |
| export const PREFIX_FILE = 'File: '; | |
| export const PREFIX_SIZE = 'Size: '; | |
| export const PREFIX_MIME = 'MIME: '; | |
| /** Byte count of the `Size: ` header line, e.g. `Size: 12345 bytes` -> capture group 1 is `12345`. */ | |
| export const READ_MEDIA_SIZE_REGEX = new RegExp(`^${PREFIX_SIZE}\\s*(\\d+)\\s*bytes`); | |
| /** Image extensions the tool accepts. The server decodes images with stb_image, which has no webp or tiff. */ | |
| export const READ_MEDIA_IMAGE_MIME: Record<string, string> = { | |
| gif: MimeTypeImage.GIF, | |
| jpeg: MimeTypeImage.JPEG, | |
| jpg: MimeTypeImage.JPEG, | |
| png: MimeTypeImage.PNG | |
| } as const; | |
| /** Audio extensions the tool accepts. The `input_audio` API only takes wav and mp3. */ | |
| export const READ_MEDIA_AUDIO_MIME: Record<string, string> = { | |
| mp3: MimeTypeAudio.MP3_MPEG, | |
| wav: MimeTypeAudio.WAV | |
| } as const; | |
| /** | |
| * Build the read_media tool definition for the modalities the active model has. | |
| * At least one of the two flags must be true, otherwise the tool is not offered | |
| * at all - a model that cannot see or hear has nothing to do with the bytes. | |
| */ | |
| export function buildReadMediaToolDefinition( | |
| supportsVision: boolean, | |
| supportsAudio: boolean | |
| ): OpenAIToolDefinition { | |
| const kinds: string[] = []; | |
| if (supportsVision) kinds.push(`images (${Object.keys(READ_MEDIA_IMAGE_MIME).join(', ')})`); | |
| if (supportsAudio) kinds.push(`audio (${Object.keys(READ_MEDIA_AUDIO_MIME).join(', ')})`); | |
| return { | |
| function: { | |
| description: `Read a media file and attach it to the conversation so it can be perceived directly. Supports ${kinds.join(' and ')}.`, | |
| name: READ_MEDIA_TOOL_NAME, | |
| parameters: { | |
| properties: { | |
| path: { | |
| description: 'Path to the media file', | |
| type: JsonSchemaType.STRING | |
| } | |
| }, | |
| required: ['path'], | |
| type: JsonSchemaType.OBJECT | |
| } | |
| }, | |
| type: ToolCallType.FUNCTION | |
| }; | |
| } | |