Instructions to use kaisser/LLM-Maroc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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

LLM-Maroc / llama.cpp /tests /CMakeLists.txt

kaisser

Upload folder using huggingface_hub

305a42c verified about 1 year ago

Raw

History Blame Contribute Delete

9.56 kB

	llama_add_compile_flags()

	function(llama_build source)
	if (DEFINED LLAMA_TEST_NAME)
	set(TEST_TARGET ${LLAMA_TEST_NAME})
	else()
	get_filename_component(TEST_TARGET ${source} NAME_WE)
	endif()

	add_executable(${TEST_TARGET} ${source})
	target_link_libraries(${TEST_TARGET} PRIVATE common)
	install(TARGETS ${TEST_TARGET} RUNTIME)
	endfunction()

	function(llama_test target)
	include(CMakeParseArguments)
	set(options)
	set(oneValueArgs NAME LABEL WORKING_DIRECTORY)
	set(multiValueArgs ARGS)
	cmake_parse_arguments(LLAMA_TEST "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})

	if (NOT DEFINED LLAMA_TEST_LABEL)
	set(LLAMA_TEST_LABEL "main")
	endif()
	if (NOT DEFINED LLAMA_TEST_WORKING_DIRECTORY)
	set(LLAMA_TEST_WORKING_DIRECTORY .)
	endif()
	if (DEFINED LLAMA_TEST_NAME)
	set(TEST_NAME ${LLAMA_TEST_NAME})
	else()
	set(TEST_NAME ${target})
	endif()

	set(TEST_TARGET ${target})

	add_test(
	NAME ${TEST_NAME}
	WORKING_DIRECTORY ${LLAMA_TEST_WORKING_DIRECTORY}
	COMMAND $<TARGET_FILE:${TEST_TARGET}>
	${LLAMA_TEST_ARGS})

	set_property(TEST ${TEST_NAME} PROPERTY LABELS ${LLAMA_TEST_LABEL})
	endfunction()

	function(llama_test_cmd target)
	include(CMakeParseArguments)
	set(options)
	set(oneValueArgs NAME LABEL WORKING_DIRECTORY)
	set(multiValueArgs ARGS)
	cmake_parse_arguments(LLAMA_TEST "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})

	if (NOT DEFINED LLAMA_TEST_LABEL)
	set(LLAMA_TEST_LABEL "main")
	endif()
	if (NOT DEFINED LLAMA_TEST_WORKING_DIRECTORY)
	set(LLAMA_TEST_WORKING_DIRECTORY .)
	endif()
	if (DEFINED LLAMA_TEST_NAME)
	set(TEST_NAME ${LLAMA_TEST_NAME})
	else()
	set(TEST_NAME ${target})
	endif()

	add_test(
	NAME ${TEST_NAME}
	WORKING_DIRECTORY ${LLAMA_TEST_WORKING_DIRECTORY}
	COMMAND ${target}
	${LLAMA_TEST_ARGS})

	set_property(TEST ${TEST_NAME} PROPERTY LABELS ${LLAMA_TEST_LABEL})
	endfunction()

	# Builds and runs a test source file.
	# Optional args:
	# - NAME: name of the executable & test target (defaults to the source file name without extension)
	# - LABEL: label for the test (defaults to main)
	# - ARGS: arguments to pass to the test executable
	# - WORKING_DIRECTORY
	function(llama_build_and_test source)
	include(CMakeParseArguments)
	set(options)
	set(oneValueArgs NAME LABEL WORKING_DIRECTORY)
	set(multiValueArgs ARGS)
	cmake_parse_arguments(LLAMA_TEST "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})

	if (NOT DEFINED LLAMA_TEST_LABEL)
	set(LLAMA_TEST_LABEL "main")
	endif()
	if (NOT DEFINED LLAMA_TEST_WORKING_DIRECTORY)
	set(LLAMA_TEST_WORKING_DIRECTORY .)
	endif()
	if (DEFINED LLAMA_TEST_NAME)
	set(TEST_TARGET ${LLAMA_TEST_NAME})
	else()
	get_filename_component(TEST_TARGET ${source} NAME_WE)
	endif()

	add_executable(${TEST_TARGET} ${source} get-model.cpp)
	install(TARGETS ${TEST_TARGET} RUNTIME)
	target_link_libraries(${TEST_TARGET} PRIVATE common)

	add_test(
	NAME ${TEST_TARGET}
	WORKING_DIRECTORY ${LLAMA_TEST_WORKING_DIRECTORY}
	COMMAND $<TARGET_FILE:${TEST_TARGET}>
	${LLAMA_TEST_ARGS})

	set_property(TEST ${TEST_TARGET} PROPERTY LABELS ${LLAMA_TEST_LABEL})
	endfunction()

	# build test-tokenizer-0 target once and add many tests
	llama_build(test-tokenizer-0.cpp)

	llama_test(test-tokenizer-0 NAME test-tokenizer-0-bert-bge ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-bert-bge.gguf)
	llama_test(test-tokenizer-0 NAME test-tokenizer-0-command-r ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-command-r.gguf)
	llama_test(test-tokenizer-0 NAME test-tokenizer-0-deepseek-coder ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-deepseek-coder.gguf)
	llama_test(test-tokenizer-0 NAME test-tokenizer-0-deepseek-llm ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-deepseek-llm.gguf)
	llama_test(test-tokenizer-0 NAME test-tokenizer-0-falcon ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-falcon.gguf)
	llama_test(test-tokenizer-0 NAME test-tokenizer-0-gpt-2 ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-gpt-2.gguf)
	llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-bpe ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-bpe.gguf)
	llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-spm ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-spm.gguf)
	llama_test(test-tokenizer-0 NAME test-tokenizer-0-mpt ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-mpt.gguf)
	llama_test(test-tokenizer-0 NAME test-tokenizer-0-phi-3 ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-phi-3.gguf)
	llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen2 ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-qwen2.gguf)
	llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-refact.gguf)
	llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-starcoder.gguf)

	if (NOT WIN32)
	llama_test_cmd(
	${CMAKE_CURRENT_SOURCE_DIR}/test-tokenizers-repo.sh
	NAME test-tokenizers-ggml-vocabs
	WORKING_DIRECTORY ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}
	ARGS https://huggingface.co/ggml-org/vocabs ${PROJECT_SOURCE_DIR}/models/ggml-vocabs
	)
	endif()

	if (LLAMA_LLGUIDANCE)
	llama_build_and_test(test-grammar-llguidance.cpp ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-bpe.gguf)
	endif ()

	if (NOT WIN32 OR NOT BUILD_SHARED_LIBS)
	# these tests are disabled on Windows because they use internal functions not exported with LLAMA_API (when building with shared libraries)
	llama_build_and_test(test-sampling.cpp)
	llama_build_and_test(test-grammar-parser.cpp)
	llama_build_and_test(test-grammar-integration.cpp)
	llama_build_and_test(test-llama-grammar.cpp)
	llama_build_and_test(test-chat.cpp)
	# TODO: disabled on loongarch64 because the ggml-ci node lacks Python 3.8
	if (NOT ${CMAKE_SYSTEM_PROCESSOR} MATCHES "loongarch64")
	llama_build_and_test(test-json-schema-to-grammar.cpp WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
	target_include_directories(test-json-schema-to-grammar PRIVATE ${PROJECT_SOURCE_DIR}/tools/server)
	endif()

	if (NOT GGML_BACKEND_DL)
	llama_build(test-quantize-stats.cpp)
	endif()

	llama_build(test-gbnf-validator.cpp)

	# build test-tokenizer-1-bpe target once and add many tests
	llama_build(test-tokenizer-1-bpe.cpp)

	# TODO: disabled due to slowness
	#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-aquila ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-aquila.gguf)
	#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-falcon ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-falcon.gguf)
	#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-gpt-2 ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-gpt-2.gguf)
	#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-gpt-neox ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-gpt-neox.gguf)
	#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-llama-bpe ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-bpe.gguf --ignore-merges)
	#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-mpt ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-mpt.gguf)
	#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-refact ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-refact.gguf)
	#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-starcoder ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-starcoder.gguf)

	# build test-tokenizer-1-spm target once and add many tests
	llama_build(test-tokenizer-1-spm.cpp)

	llama_test(test-tokenizer-1-spm NAME test-tokenizer-1-llama-spm ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-spm.gguf)
	#llama_test(test-tokenizer-1-spm NAME test-tokenizer-1-baichuan ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-baichuan.gguf)

	# llama_build_and_test(test-double-float.cpp) # SLOW
	endif()

	llama_build_and_test(test-chat-parser.cpp)
	llama_build_and_test(test-chat-template.cpp)
	llama_build_and_test(test-json-partial.cpp)
	llama_build_and_test(test-log.cpp)
	llama_build_and_test(test-regex-partial.cpp)

	llama_build_and_test(test-thread-safety.cpp ARGS -hf ggml-org/models -hff tinyllamas/stories15M-q4_0.gguf -ngl 99 -p "The meaning of life is" -n 128 -c 256 -ub 32 -np 4)

	# this fails on windows (github hosted runner) due to curl DLL not found (exit code 0xc0000135)
	if (NOT WIN32)
	llama_build_and_test(test-arg-parser.cpp)
	endif()

	# llama_build_and_test(test-opt.cpp) # SLOW
	llama_build_and_test(test-gguf.cpp)
	llama_build_and_test(test-backend-ops.cpp)

	llama_build_and_test(test-model-load-cancel.cpp LABEL "model")
	llama_build_and_test(test-autorelease.cpp LABEL "model")

	if (NOT GGML_BACKEND_DL)
	# these tests use the backends directly and cannot be built with dynamic loading
	llama_build_and_test(test-barrier.cpp)
	llama_build_and_test(test-quantize-fns.cpp)
	llama_build_and_test(test-quantize-perf.cpp)
	llama_build_and_test(test-rope.cpp)
	endif()

	# libmtmd
	set(LLAMA_TEST_NAME test-mtmd-c-api)
	llama_build_and_test(test-mtmd-c-api.c)
	target_link_libraries(${LLAMA_TEST_NAME} PRIVATE mtmd)

	# dummy executable - not installed
	get_filename_component(TEST_TARGET test-c.c NAME_WE)
	add_executable(${TEST_TARGET} test-c.c)
	target_link_libraries(${TEST_TARGET} PRIVATE llama)