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 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

LLM-Maroc / llama.cpp /docs /development /token_generation_performance_tips.md

kaisser

Upload folder using huggingface_hub

305a42c verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

2.3 kB

Token generation performance troubleshooting

Verifying that the model is running on the GPU with CUDA

Make sure you compiled llama with the correct env variables according to this guide, so that llama accepts the -ngl N (or --n-gpu-layers N) flag. When running llama, you may configure N to be very large, and llama will offload the maximum possible number of layers to the GPU, even if it's less than the number you configured. For example:

./llama-cli -m "path/to/model.gguf" -ngl 200000 -p "Please sir, may I have some "

When running llama, before it starts the inference work, it will output diagnostic information that shows whether cuBLAS is offloading work to the GPU. Look for these lines:

llama_model_load_internal: [cublas] offloading 60 layers to GPU
llama_model_load_internal: [cublas] offloading output layer to GPU
llama_model_load_internal: [cublas] total VRAM used: 17223 MB
... rest of inference

If you see these lines, then the GPU is being used.

Verifying that the CPU is not oversaturated

llama accepts a -t N (or --threads N) parameter. It's extremely important that this parameter is not too large. If your token generation is extremely slow, try setting this number to 1. If this significantly improves your token generation speed, then your CPU is being oversaturated and you need to explicitly set this parameter to the number of the physical CPU cores on your machine (even if you utilize a GPU). If in doubt, start with 1 and double the amount until you hit a performance bottleneck, then scale the number down.

Example of runtime flags effect on inference speed benchmark

These runs were tested on the following machine: GPU: A6000 (48GB VRAM) CPU: 7 physical cores RAM: 32GB

Model: TheBloke_Wizard-Vicuna-30B-Uncensored-GGML/Wizard-Vicuna-30B-Uncensored.q4_0.gguf (30B parameters, 4bit quantization, GGML)

Run command: ./llama-cli -m "path/to/model.gguf" -p "An extremely detailed description of the 10 best ethnic dishes will follow, with recipes: " -n 1000 [additional benchmark flags]

Result:

command	tokens/second (higher is better)
-ngl 2000000	N/A (less than 0.1)
-t 7	1.7
-t 1 -ngl 2000000	5.5
-t 7 -ngl 2000000	8.7
-t 4 -ngl 2000000	9.1