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/agentic.constants.ts from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 2.5 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/src/lib/constants/agentic.constants.ts
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/tools/ui/src/lib/constants/agentic.constants.ts
-
curl -L -o agentic.constants.ts https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/tools/ui/src/lib/constants/agentic.constants.ts
2.5 kB
| import type { AgenticConfig } from '$lib/types/agentic'; | |
| export const ATTACHMENT_SAVED_REGEX = /\[Attachment saved: ([^\]]+)\]/; | |
| // JSON detection: trimmed content opens with an object or array literal. | |
| export const TOOL_RESULT_JSON_OPEN_REGEX = /^[[{]/; | |
| // Search-summary wire format used by file-glob and grep tools: | |
| // <matches> | |
| // --- | |
| // Total matches: N | |
| export const SEARCH_SUMMARY = { | |
| SEPARATOR: '---\n', | |
| TOTAL_REGEX: /Total matches:\s*(\d+)/ | |
| } as const; | |
| // Separator rendered between stats in the tool-result footer (e.g. between a | |
| // result message and the byte/edit count). Plain ASCII spaces bracket a hyphen | |
| // so the whole " - " sits on one visual line even when the surrounding text | |
| // wraps mid-paragraph. | |
| export const RESULT_STAT_SEPARATOR = ' - '; | |
| export const DEFAULT_AGENTIC_CONFIG: AgenticConfig = { | |
| enabled: true, | |
| maxTurns: 100 | |
| } as const; | |
| export const REASONING_TAGS = { | |
| END: '</think>', | |
| START: '<think>' | |
| } as const; | |
| /** | |
| * @deprecated Legacy marker tags - only used for migration of old stored messages. | |
| * New messages use structured fields (reasoningContent, toolCalls, toolCallId). | |
| */ | |
| export const LEGACY_AGENTIC_TAGS = { | |
| TAG_SUFFIX: '>>>', | |
| TOOL_ARGS_END: '<<<TOOL_ARGS_END>>>', | |
| TOOL_ARGS_START: '<<<TOOL_ARGS_START>>>', | |
| TOOL_CALL_END: '<<<AGENTIC_TOOL_CALL_END>>>', | |
| TOOL_CALL_START: '<<<AGENTIC_TOOL_CALL_START>>>', | |
| TOOL_NAME_PREFIX: '<<<TOOL_NAME:' | |
| } as const; | |
| /** | |
| * @deprecated Legacy reasoning tags - only used for migration of old stored messages. | |
| * New messages use the dedicated reasoningContent field. | |
| */ | |
| export const LEGACY_REASONING_TAGS = { | |
| END: '<<<reasoning_content_end>>>', | |
| START: '<<<reasoning_content_start>>>' | |
| } as const; | |
| /** | |
| * @deprecated Legacy regex patterns - only used for migration of old stored messages. | |
| */ | |
| export const LEGACY_AGENTIC_REGEX = { | |
| AGENTIC_TOOL_CALL_BLOCK: /\n*<<<AGENTIC_TOOL_CALL_START>>>[\s\S]*?<<<AGENTIC_TOOL_CALL_END>>>/g, | |
| AGENTIC_TOOL_CALL_OPEN: /\n*<<<AGENTIC_TOOL_CALL_START>>>[\s\S]*$/, | |
| COMPLETED_TOOL_CALL: | |
| /<<<AGENTIC_TOOL_CALL_START>>>\n<<<TOOL_NAME:(.+?)>>>\n<<<TOOL_ARGS_START>>>([\s\S]*?)<<<TOOL_ARGS_END>>>([\s\S]*?)<<<AGENTIC_TOOL_CALL_END>>>/g, | |
| HAS_LEGACY_MARKERS: /<<<(?:AGENTIC_TOOL_CALL_START|reasoning_content_start)>>>/, | |
| REASONING_BLOCK: /<<<reasoning_content_start>>>[\s\S]*?<<<reasoning_content_end>>>/g, | |
| REASONING_EXTRACT: /<<<reasoning_content_start>>>([\s\S]*?)<<<reasoning_content_end>>>/, | |
| REASONING_OPEN: /<<<reasoning_content_start>>>[\s\S]*$/ | |
| } as const; | |