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/utils/parse-exec-shell-status.ts from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 1.54 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/src/lib/utils/parse-exec-shell-status.ts
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/tools/ui/src/lib/utils/parse-exec-shell-status.ts
-
curl -L -o parse-exec-shell-status.ts https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/src/lib/utils/parse-exec-shell-status.ts
1.54 kB
| /** | |
| * Parsing helpers for `exec_shell_command` tool output. | |
| * | |
| * The server appends one final line to the response - an exit-code summary | |
| * shaped as `[exit code: N]` (and optionally followed by `[exit due to timed | |
| * out]`) - so the renderer can color that final line based on success/failure | |
| * without parsing the entire output stream. | |
| */ | |
| export interface ExecShellExitStatus { | |
| code: number; | |
| timedOut: boolean; | |
| /** Length-prefix slice for matching against the rendered lines list. */ | |
| rawText: string; | |
| } | |
| // Anchor to the absolute end so intermediate "[exit code: N]" string content | |
| // (e.g. a shell echo) doesn't false-positive. | |
| const EXIT_CODE_TAIL_REGEX = /\[exit code: (-?\d+)\](?: \[exit due to timed out\])?\s*$/; | |
| export function parseExecShellCommandExitStatus( | |
| toolResultString: string | undefined | |
| ): ExecShellExitStatus | undefined { | |
| if (!toolResultString) return undefined; | |
| const match = toolResultString.match(EXIT_CODE_TAIL_REGEX); | |
| if (!match) return undefined; | |
| return { | |
| code: Number.parseInt(match[1], 10), | |
| rawText: match[0], | |
| timedOut: match[0].includes('exit due to timed out') | |
| }; | |
| } | |
| /** | |
| * Returns true when the supplied rendered line equals (trimmed) the | |
| * trailing exit-code text. Used by the renderer to drop the duplicated | |
| * representation (since the trailing line is replaced by a status badge). | |
| */ | |
| export function isExitCodeSummaryLine( | |
| lineText: string, | |
| status: ExecShellExitStatus | undefined | |
| ): boolean { | |
| if (!status) return false; | |
| return lineText.trim() === status.rawText.trim(); | |
| } | |