Text Generation
Transformers
Safetensors
GGUF
llama
chatbot
multilingual
arabic
french
tamazight
english
conversational
text-generation-inference
4-bit precision
bitsandbytes
Instructions to use kaisser/LLM-Maroc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kaisser/LLM-Maroc with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kaisser/LLM-Maroc") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("kaisser/LLM-Maroc") model = AutoModelForCausalLM.from_pretrained("kaisser/LLM-Maroc", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use kaisser/LLM-Maroc 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 kaisser/LLM-Maroc:BF16 # Run inference directly in the terminal: llama cli -hf kaisser/LLM-Maroc:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf kaisser/LLM-Maroc:BF16 # Run inference directly in the terminal: llama cli -hf kaisser/LLM-Maroc:BF16
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 kaisser/LLM-Maroc:BF16 # Run inference directly in the terminal: ./llama-cli -hf kaisser/LLM-Maroc:BF16
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 kaisser/LLM-Maroc:BF16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf kaisser/LLM-Maroc:BF16
Use Docker
docker model run hf.co/kaisser/LLM-Maroc:BF16
- LM Studio
- Jan
- vLLM
How to use kaisser/LLM-Maroc with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kaisser/LLM-Maroc" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kaisser/LLM-Maroc", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/kaisser/LLM-Maroc:BF16
- SGLang
How to use kaisser/LLM-Maroc with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "kaisser/LLM-Maroc" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kaisser/LLM-Maroc", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "kaisser/LLM-Maroc" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kaisser/LLM-Maroc", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use kaisser/LLM-Maroc with Ollama:
ollama run hf.co/kaisser/LLM-Maroc:BF16
- Unsloth Desktop
- Docker Model Runner
How to use kaisser/LLM-Maroc with Docker Model Runner:
docker model run hf.co/kaisser/LLM-Maroc:BF16
- Lemonade
How to use kaisser/LLM-Maroc with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull kaisser/LLM-Maroc:BF16
Run and chat with the model
lemonade run user.LLM-Maroc-BF16
List all available models
lemonade list
- Atomic Chat
| 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) | |
| set(CMAKE_LIBRARY_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() | |
| option(LLAMA_USE_SYSTEM_GGML "Use system libggml" OFF) | |
| 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" ${BUILD_SHARED_LIBS_DEFAULT}) | |
| if (WIN32) | |
| add_compile_definitions(_CRT_SECURE_NO_WARNINGS) | |
| endif() | |
| if (MSVC) | |
| add_compile_options("$<$<COMPILE_LANGUAGE:C>:/utf-8>") | |
| add_compile_options("$<$<COMPILE_LANGUAGE:CXX>:/utf-8>") | |
| add_compile_options("$<$<COMPILE_LANGUAGE:C>:/bigobj>") | |
| add_compile_options("$<$<COMPILE_LANGUAGE:CXX>:/bigobj>") | |
| 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_TOOLS "llama: build tools" ${LLAMA_STANDALONE}) | |
| option(LLAMA_BUILD_EXAMPLES "llama: build examples" ${LLAMA_STANDALONE}) | |
| option(LLAMA_BUILD_SERVER "llama: build server example" ${LLAMA_STANDALONE}) | |
| # 3rd party libs | |
| option(LLAMA_CURL "llama: use libcurl to download model from an URL" ON) | |
| option(LLAMA_LLGUIDANCE "llama-common: include LLGuidance library for structured output in common utils" OFF) | |
| # Required for relocatable CMake package | |
| include(${CMAKE_CURRENT_SOURCE_DIR}/cmake/build-info.cmake) | |
| include(${CMAKE_CURRENT_SOURCE_DIR}/cmake/common.cmake) | |
| if (NOT DEFINED LLAMA_BUILD_NUMBER) | |
| set(LLAMA_BUILD_NUMBER ${BUILD_NUMBER}) | |
| endif() | |
| if (NOT DEFINED LLAMA_BUILD_COMMIT) | |
| set(LLAMA_BUILD_COMMIT ${BUILD_COMMIT}) | |
| endif() | |
| set(LLAMA_INSTALL_VERSION 0.0.${LLAMA_BUILD_NUMBER}) | |
| # override ggml options | |
| 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_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) | |
| if (NOT MSVC) | |
| if (LLAMA_SANITIZE_THREAD) | |
| message(STATUS "Using -fsanitize=thread") | |
| add_compile_options(-fsanitize=thread) | |
| link_libraries (-fsanitize=thread) | |
| endif() | |
| if (LLAMA_SANITIZE_ADDRESS) | |
| message(STATUS "Using -fsanitize=address") | |
| add_compile_options(-fsanitize=address -fno-omit-frame-pointer) | |
| link_libraries (-fsanitize=address) | |
| endif() | |
| if (LLAMA_SANITIZE_UNDEFINED) | |
| message(STATUS "Using -fsanitize=undefined") | |
| add_compile_options(-fsanitize=undefined) | |
| link_libraries (-fsanitize=undefined) | |
| endif() | |
| endif() | |
| # | |
| # 3rd-party | |
| # | |
| if (LLAMA_USE_SYSTEM_GGML) | |
| message(STATUS "Using system-provided libggml, skipping ggml build") | |
| find_package(ggml REQUIRED) | |
| add_library(ggml ALIAS ggml::ggml) | |
| endif() | |
| if (NOT TARGET ggml AND NOT LLAMA_USE_SYSTEM_GGML) | |
| set(GGML_BUILD_NUMBER ${LLAMA_BUILD_NUMBER}) | |
| set(GGML_BUILD_COMMIT ${LLAMA_BUILD_COMMIT}) | |
| add_subdirectory(ggml) | |
| # ... otherwise assume ggml is added by a parent CMakeLists.txt | |
| endif() | |
| if (MINGW) | |
| # Target Windows 8 for PrefetchVirtualMemory | |
| add_compile_definitions(_WIN32_WINNT=${GGML_WIN_VER}) | |
| endif() | |
| # | |
| # build the library | |
| # | |
| add_subdirectory(src) | |
| # | |
| # utils, programs, examples and tests | |
| # | |
| if (NOT LLAMA_BUILD_COMMON) | |
| message(STATUS "LLAMA_BUILD_COMMON is OFF, disabling LLAMA_CURL") | |
| set(LLAMA_CURL OFF) | |
| endif() | |
| if (LLAMA_BUILD_COMMON) | |
| add_subdirectory(common) | |
| endif() | |
| if (LLAMA_BUILD_COMMON AND LLAMA_BUILD_TESTS AND NOT CMAKE_JS_VERSION) | |
| include(CTest) | |
| add_subdirectory(tests) | |
| endif() | |
| if (LLAMA_BUILD_COMMON AND LLAMA_BUILD_EXAMPLES) | |
| add_subdirectory(examples) | |
| add_subdirectory(pocs) | |
| endif() | |
| if (LLAMA_BUILD_COMMON AND LLAMA_BUILD_TOOLS) | |
| add_subdirectory(tools) | |
| endif() | |
| # | |
| # install | |
| # | |
| include(GNUInstallDirs) | |
| include(CMakePackageConfigHelpers) | |
| 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") | |
| set(LLAMA_PUBLIC_HEADERS | |
| ${CMAKE_CURRENT_SOURCE_DIR}/include/llama.h | |
| ${CMAKE_CURRENT_SOURCE_DIR}/include/llama-cpp.h) | |
| set_target_properties(llama | |
| PROPERTIES | |
| PUBLIC_HEADER "${LLAMA_PUBLIC_HEADERS}") | |
| 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 ${CMAKE_INSTALL_LIBDIR}/pkgconfig) | |