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 /src /llama-adapter.h

kaisser

Upload folder using huggingface_hub

305a42c verified about 1 year ago

Raw

History Blame Contribute Delete

1.76 kB

	#pragma once

	#include "llama.h"

	#include "ggml-cpp.h"

	#include <string>
	#include <unordered_map>
	#include <vector>

	// TODO: pimpl

	//
	// llama_adapter_cvec
	//

	struct llama_adapter_cvec {
	ggml_tensor * tensor_for(int il) const;

	ggml_tensor * apply_to(ggml_context * ctx, ggml_tensor * cur, int il) const;

	bool apply(
	const llama_model & model,
	const float * data,
	size_t len,
	int32_t n_embd,
	int32_t il_start,
	int32_t il_end);

	private:
	bool init(const llama_model & model);

	int32_t layer_start = -1;
	int32_t layer_end = -1;

	std::vector<ggml_context_ptr> ctxs;
	std::vector<ggml_backend_buffer_ptr> bufs;

	std::vector<ggml_tensor *> tensors; // per layer
	};

	//
	// llama_adapter_lora
	//

	struct llama_adapter_lora_weight {
	ggml_tensor * a = nullptr;
	ggml_tensor * b = nullptr;

	// get actual scale based on rank and alpha
	float get_scale(float alpha, float adapter_scale) const {
	const float rank = (float) b->ne[0];
	const float scale = alpha ? adapter_scale * alpha / rank : adapter_scale;
	return scale;
	}

	llama_adapter_lora_weight() = default;
	llama_adapter_lora_weight(ggml_tensor * a, ggml_tensor * b) : a(a), b(b) {}
	};

	struct llama_adapter_lora {
	// map tensor name to lora_a_b
	std::unordered_map<std::string, llama_adapter_lora_weight> ab_map;

	std::vector<ggml_context_ptr> ctxs;
	std::vector<ggml_backend_buffer_ptr> bufs;

	float alpha;

	llama_adapter_lora() = default;
	~llama_adapter_lora() = default;

	llama_adapter_lora_weight * get_weight(ggml_tensor * w);
	};

	using llama_adapter_loras = std::unordered_map<llama_adapter_lora *, float>;