Text Generation
GGUF
English
llama.cpp
bitnet
ternary
1.58-bit
quantized
q4_k_m
edge
efficient-inference
cpu
tool-calling
Instructions to use Qapdex/SLM750-Edge-1.58-bit 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 Qapdex/SLM750-Edge-1.58-bit 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 Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT # Run inference directly in the terminal: llama cli -hf Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT # Run inference directly in the terminal: llama cli -hf Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT # Run inference directly in the terminal: ./llama-cli -hf Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT # Run inference directly in the terminal: ./build/bin/llama-cli -hf Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
Use Docker
docker model run hf.co/Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
- LM Studio
- Jan
- vLLM
How to use Qapdex/SLM750-Edge-1.58-bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qapdex/SLM750-Edge-1.58-bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qapdex/SLM750-Edge-1.58-bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
- Ollama
How to use Qapdex/SLM750-Edge-1.58-bit with Ollama:
ollama run hf.co/Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
- Unsloth Studio
How to use Qapdex/SLM750-Edge-1.58-bit with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Qapdex/SLM750-Edge-1.58-bit to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Qapdex/SLM750-Edge-1.58-bit to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Qapdex/SLM750-Edge-1.58-bit to start chatting
- Atomic Chat new
- Docker Model Runner
How to use Qapdex/SLM750-Edge-1.58-bit with Docker Model Runner:
docker model run hf.co/Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
- Lemonade
How to use Qapdex/SLM750-Edge-1.58-bit with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Qapdex/SLM750-Edge-1.58-bit:Q4_K_M_QUANT
Run and chat with the model
lemonade run user.SLM750-Edge-1.58-bit-Q4_K_M_QUANT
List all available models
lemonade list
| cmake_minimum_required(VERSION 3.14) # for add_link_options and implicit target directories. | |
| project("llama.cpp" C CXX) | |
| include(CheckIncludeFileCXX) | |
| #set(CMAKE_WARN_DEPRECATED YES) | |
| set(CMAKE_WARN_UNUSED_CLI YES) | |
| set(CMAKE_EXPORT_COMPILE_COMMANDS ON) | |
| if (NOT XCODE AND NOT MSVC AND NOT CMAKE_BUILD_TYPE) | |
| set(CMAKE_BUILD_TYPE Release CACHE STRING "Build type" FORCE) | |
| set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS "Debug" "Release" "MinSizeRel" "RelWithDebInfo") | |
| endif() | |
| # Add path to modules | |
| list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake/") | |
| set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin) | |
| if (CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR) | |
| set(LLAMA_STANDALONE ON) | |
| include(git-vars) | |
| # configure project version | |
| # TODO | |
| else() | |
| set(LLAMA_STANDALONE OFF) | |
| endif() | |
| if (EMSCRIPTEN) | |
| set(BUILD_SHARED_LIBS_DEFAULT OFF) | |
| option(LLAMA_WASM_SINGLE_FILE "llama: embed WASM inside the generated llama.js" ON) | |
| else() | |
| if (MINGW) | |
| set(BUILD_SHARED_LIBS_DEFAULT OFF) | |
| else() | |
| set(BUILD_SHARED_LIBS_DEFAULT ON) | |
| endif() | |
| endif() | |
| option(BUILD_SHARED_LIBS "build shared libraries" ${BUILD_SHARED_LIBS_DEFAULT}) | |
| if (WIN32) | |
| add_compile_definitions(_CRT_SECURE_NO_WARNINGS) | |
| endif() | |
| # | |
| # option list | |
| # | |
| # debug | |
| option(LLAMA_ALL_WARNINGS "llama: enable all compiler warnings" ON) | |
| option(LLAMA_ALL_WARNINGS_3RD_PARTY "llama: enable all compiler warnings in 3rd party libs" OFF) | |
| # build | |
| option(LLAMA_FATAL_WARNINGS "llama: enable -Werror flag" OFF) | |
| # sanitizers | |
| option(LLAMA_SANITIZE_THREAD "llama: enable thread sanitizer" OFF) | |
| option(LLAMA_SANITIZE_ADDRESS "llama: enable address sanitizer" OFF) | |
| option(LLAMA_SANITIZE_UNDEFINED "llama: enable undefined sanitizer" OFF) | |
| # utils | |
| option(LLAMA_BUILD_COMMON "llama: build common utils library" ${LLAMA_STANDALONE}) | |
| # extra artifacts | |
| option(LLAMA_BUILD_TESTS "llama: build tests" ${LLAMA_STANDALONE}) | |
| option(LLAMA_BUILD_EXAMPLES "llama: build examples" ${LLAMA_STANDALONE}) | |
| option(LLAMA_BUILD_SERVER "llama: build server example" ${LLAMA_STANDALONE}) | |
| # 3rd party libs | |
| option(LLAMA_CURL "llama: use libcurl to download model from an URL" OFF) | |
| # Required for relocatable CMake package | |
| include(${CMAKE_CURRENT_SOURCE_DIR}/cmake/build-info.cmake) | |
| # override ggml options | |
| set(GGML_SANITIZE_THREAD ${LLAMA_SANITIZE_THREAD}) | |
| set(GGML_SANITIZE_ADDRESS ${LLAMA_SANITIZE_ADDRESS}) | |
| set(GGML_SANITIZE_UNDEFINED ${LLAMA_SANITIZE_UNDEFINED}) | |
| set(GGML_ALL_WARNINGS ${LLAMA_ALL_WARNINGS}) | |
| set(GGML_FATAL_WARNINGS ${LLAMA_FATAL_WARNINGS}) | |
| # change the default for these ggml options | |
| if (NOT DEFINED GGML_LLAMAFILE) | |
| set(GGML_LLAMAFILE_DEFAULT ON) | |
| endif() | |
| if (NOT DEFINED GGML_CUDA_GRAPHS) | |
| set(GGML_CUDA_GRAPHS_DEFAULT ON) | |
| endif() | |
| # transition helpers | |
| function (llama_option_depr TYPE OLD NEW) | |
| if (${OLD}) | |
| message(${TYPE} "${OLD} is deprecated and will be removed in the future.\nUse ${NEW} instead\n") | |
| set(${NEW} ON PARENT_SCOPE) | |
| endif() | |
| endfunction() | |
| llama_option_depr(FATAL_ERROR LLAMA_CUBLAS GGML_CUDA) | |
| llama_option_depr(WARNING LLAMA_CUDA GGML_CUDA) | |
| llama_option_depr(WARNING LLAMA_KOMPUTE GGML_KOMPUTE) | |
| llama_option_depr(WARNING LLAMA_METAL GGML_METAL) | |
| llama_option_depr(WARNING LLAMA_METAL_EMBED_LIBRARY GGML_METAL_EMBED_LIBRARY) | |
| llama_option_depr(WARNING LLAMA_NATIVE GGML_NATIVE) | |
| llama_option_depr(WARNING LLAMA_RPC GGML_RPC) | |
| llama_option_depr(WARNING LLAMA_SYCL GGML_SYCL) | |
| llama_option_depr(WARNING LLAMA_SYCL_F16 GGML_SYCL_F16) | |
| llama_option_depr(WARNING LLAMA_CANN GGML_CANN) | |
| # | |
| # build the library | |
| # | |
| if (NOT TARGET ggml) | |
| add_subdirectory(ggml) | |
| # ... otherwise assume ggml is added by a parent CMakeLists.txt | |
| endif() | |
| add_subdirectory(src) | |
| # | |
| # install | |
| # | |
| include(GNUInstallDirs) | |
| include(CMakePackageConfigHelpers) | |
| set(LLAMA_BUILD_NUMBER ${BUILD_NUMBER}) | |
| set(LLAMA_BUILD_COMMIT ${BUILD_COMMIT}) | |
| set(LLAMA_INSTALL_VERSION 0.0.${BUILD_NUMBER}) | |
| set(LLAMA_INCLUDE_INSTALL_DIR ${CMAKE_INSTALL_INCLUDEDIR} CACHE PATH "Location of header files") | |
| set(LLAMA_LIB_INSTALL_DIR ${CMAKE_INSTALL_LIBDIR} CACHE PATH "Location of library files") | |
| set(LLAMA_BIN_INSTALL_DIR ${CMAKE_INSTALL_BINDIR} CACHE PATH "Location of binary files") | |
| # At the moment some compile definitions are placed within the ggml/src | |
| # directory but not exported on the `ggml` target. This could be improved by | |
| # determining _precisely_ which defines are necessary for the llama-config | |
| # package. | |
| # | |
| set(GGML_TRANSIENT_DEFINES) | |
| get_target_property(GGML_DIRECTORY ggml SOURCE_DIR) | |
| get_directory_property(GGML_DIR_DEFINES DIRECTORY ${GGML_DIRECTORY} COMPILE_DEFINITIONS) | |
| if (GGML_DIR_DEFINES) | |
| list(APPEND GGML_TRANSIENT_DEFINES ${GGML_DIR_DEFINES}) | |
| endif() | |
| get_target_property(GGML_TARGET_DEFINES ggml COMPILE_DEFINITIONS) | |
| if (GGML_TARGET_DEFINES) | |
| list(APPEND GGML_TRANSIENT_DEFINES ${GGML_TARGET_DEFINES}) | |
| endif() | |
| get_target_property(GGML_LINK_LIBRARIES ggml LINK_LIBRARIES) | |
| set_target_properties(llama PROPERTIES PUBLIC_HEADER ${CMAKE_CURRENT_SOURCE_DIR}/include/llama.h) | |
| install(TARGETS llama LIBRARY PUBLIC_HEADER) | |
| configure_package_config_file( | |
| ${CMAKE_CURRENT_SOURCE_DIR}/cmake/llama-config.cmake.in | |
| ${CMAKE_CURRENT_BINARY_DIR}/llama-config.cmake | |
| INSTALL_DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/llama | |
| PATH_VARS LLAMA_INCLUDE_INSTALL_DIR | |
| LLAMA_LIB_INSTALL_DIR | |
| LLAMA_BIN_INSTALL_DIR ) | |
| write_basic_package_version_file( | |
| ${CMAKE_CURRENT_BINARY_DIR}/llama-version.cmake | |
| VERSION ${LLAMA_INSTALL_VERSION} | |
| COMPATIBILITY SameMajorVersion) | |
| install(FILES ${CMAKE_CURRENT_BINARY_DIR}/llama-config.cmake | |
| ${CMAKE_CURRENT_BINARY_DIR}/llama-version.cmake | |
| DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/llama) | |
| install( | |
| FILES convert_hf_to_gguf.py | |
| PERMISSIONS | |
| OWNER_READ | |
| OWNER_WRITE | |
| OWNER_EXECUTE | |
| GROUP_READ | |
| GROUP_EXECUTE | |
| WORLD_READ | |
| WORLD_EXECUTE | |
| DESTINATION ${CMAKE_INSTALL_BINDIR}) | |
| configure_file(cmake/llama.pc.in | |
| "${CMAKE_CURRENT_BINARY_DIR}/llama.pc" | |
| @ONLY) | |
| install(FILES "${CMAKE_CURRENT_BINARY_DIR}/llama.pc" | |
| DESTINATION lib/pkgconfig) | |
| # | |
| # utils, programs, examples and tests | |
| # | |
| add_subdirectory(common) | |
| add_subdirectory(examples) | |