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 Studio
How to use kaisser/LLM-Maroc 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 kaisser/LLM-Maroc 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 kaisser/LLM-Maroc to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for kaisser/LLM-Maroc to start chatting
- 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
| template <class T> static void assert_equals(const T & expected, const T & actual) { | |
| if (expected != actual) { | |
| std::cerr << "Expected: " << expected << std::endl; | |
| std::cerr << "Actual: " << actual << std::endl; | |
| std::cerr << std::flush; | |
| throw std::runtime_error("Test failed"); | |
| } | |
| } | |
| static void test_json_healing() { | |
| auto parse = [](const std::string & str) { | |
| std::cerr << "# Parsing: " << str << '\n'; | |
| std::string::const_iterator it = str.begin(); | |
| const auto end = str.end(); | |
| common_json out; | |
| std::string healing_marker = "$llama.cpp.json$"; | |
| if (common_json_parse(it, end, healing_marker, out)) { | |
| auto dump = out.json.dump(); | |
| std::cerr << "Parsed: " << dump << '\n'; | |
| std::cerr << "Magic: " << out.healing_marker.json_dump_marker << '\n'; | |
| std::string result; | |
| if (!out.healing_marker.json_dump_marker.empty()) { | |
| auto i = dump.find(out.healing_marker.json_dump_marker); | |
| if (i == std::string::npos) { | |
| throw std::runtime_error("Failed to find magic in dump " + dump + " (magic: " + out.healing_marker.json_dump_marker + ")"); | |
| } | |
| result = dump.substr(0, i); | |
| } else { | |
| result = dump; | |
| } | |
| std::cerr << "Result: " << result << '\n'; | |
| if (string_starts_with(str, result)) { | |
| std::cerr << "Failure!\n"; | |
| } | |
| // return dump; | |
| } else { | |
| throw std::runtime_error("Failed to parse: " + str); | |
| } | |
| }; | |
| auto parse_all = [&](const std::string & str) { | |
| for (size_t i = 1; i < str.size(); i++) { | |
| parse(str.substr(0, i)); | |
| } | |
| }; | |
| parse_all("{\"a\": \"b\"}"); | |
| parse_all("{\"hey\": 1, \"ho\\\"ha\": [1]}"); | |
| parse_all("[{\"a\": \"b\"}]"); | |
| auto test = [&](const std::vector<std::string> & inputs, const std::string & expected, const std::string & expected_marker) { | |
| for (const auto & input : inputs) { | |
| common_json out; | |
| assert_equals(true, common_json_parse(input, "$foo", out)); | |
| assert_equals<std::string>(expected, out.json.dump()); | |
| assert_equals<std::string>(expected_marker, out.healing_marker.json_dump_marker); | |
| } | |
| }; | |
| // No healing needed: | |
| test( | |
| { | |
| R"([{"a":"b"}, "y"])", | |
| }, | |
| R"([{"a":"b"},"y"])", | |
| "" | |
| ); | |
| // Partial literals can't be healed: | |
| test( | |
| { | |
| R"([1)", | |
| R"([tru)", | |
| R"([n)", | |
| R"([nul)", | |
| R"([23.2)", | |
| }, | |
| R"(["$foo"])", | |
| R"("$foo)" | |
| ); | |
| test( | |
| { | |
| R"({"a": 1)", | |
| R"({"a": tru)", | |
| R"({"a": n)", | |
| R"({"a": nul)", | |
| R"({"a": 23.2)", | |
| }, | |
| R"({"a":"$foo"})", | |
| R"("$foo)" | |
| ); | |
| test( | |
| { | |
| R"({)", | |
| }, | |
| R"({"$foo":1})", | |
| R"("$foo)" | |
| ); | |
| test( | |
| { | |
| R"([)", | |
| }, | |
| R"(["$foo"])", | |
| R"("$foo)" | |
| ); | |
| // Healing right after a full literal | |
| test( | |
| { | |
| R"(1 )", | |
| }, | |
| R"(1)", | |
| "" | |
| ); | |
| test( | |
| { | |
| R"(true)", | |
| R"(true )", | |
| }, | |
| R"(true)", | |
| "" | |
| ); | |
| test( | |
| { | |
| R"(null)", | |
| R"(null )", | |
| }, | |
| R"(null)", | |
| "" | |
| ); | |
| test( | |
| { | |
| R"([1 )", | |
| }, | |
| R"([1,"$foo"])", | |
| R"(,"$foo)" | |
| ); | |
| test( | |
| { | |
| R"([{})", | |
| R"([{} )", | |
| }, | |
| R"([{},"$foo"])", | |
| R"(,"$foo)" | |
| ); | |
| test( | |
| { | |
| R"([true)", | |
| }, | |
| // TODO: detect the true/false/null literal was complete | |
| R"(["$foo"])", | |
| R"("$foo)" | |
| ); | |
| test( | |
| { | |
| R"([true )", | |
| }, | |
| R"([true,"$foo"])", | |
| R"(,"$foo)" | |
| ); | |
| test( | |
| { | |
| R"([true,)", | |
| }, | |
| R"([true,"$foo"])", | |
| R"("$foo)" | |
| ); | |
| // Test nesting | |
| test( | |
| { | |
| R"([{"a": [{"b": [{)", | |
| }, | |
| R"([{"a":[{"b":[{"$foo":1}]}]}])", | |
| R"("$foo)" | |
| ); | |
| test( | |
| { | |
| R"([{"a": [{"b": [)", | |
| }, | |
| R"([{"a":[{"b":["$foo"]}]}])", | |
| R"("$foo)" | |
| ); | |
| test( | |
| { | |
| R"([{"a": "b"})", | |
| R"([{"a": "b"} )", | |
| }, | |
| R"([{"a":"b"},"$foo"])", | |
| R"(,"$foo)" | |
| ); | |
| test( | |
| { | |
| R"([{"a": "b"},)", | |
| R"([{"a": "b"}, )", | |
| }, | |
| R"([{"a":"b"},"$foo"])", | |
| R"("$foo)" | |
| ); | |
| test( | |
| { | |
| R"({ "code)", | |
| }, | |
| R"({"code$foo":1})", | |
| R"($foo)" | |
| ); | |
| test( | |
| { | |
| R"({ "code\)", | |
| }, | |
| R"({"code\\$foo":1})", | |
| R"(\$foo)" | |
| ); | |
| test( | |
| { | |
| R"({ "code")", | |
| }, | |
| R"({"code":"$foo"})", | |
| R"(:"$foo)" | |
| ); | |
| test( | |
| { | |
| R"({ "key")", | |
| }, | |
| R"({"key":"$foo"})", | |
| R"(:"$foo)" | |
| ); | |
| } | |
| int main() { | |
| test_json_healing(); | |
| std::cerr << "All tests passed.\n"; | |
| return 0; | |
| } | |