Instructions to use paulml/ECE-ILAB-Q1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use paulml/ECE-ILAB-Q1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="paulml/ECE-ILAB-Q1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("paulml/ECE-ILAB-Q1")
model = AutoModelForCausalLM.from_pretrained("paulml/ECE-ILAB-Q1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use paulml/ECE-ILAB-Q1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "paulml/ECE-ILAB-Q1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "paulml/ECE-ILAB-Q1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/paulml/ECE-ILAB-Q1

SGLang

How to use paulml/ECE-ILAB-Q1 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 "paulml/ECE-ILAB-Q1" \
    --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": "paulml/ECE-ILAB-Q1",
		"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 "paulml/ECE-ILAB-Q1" \
        --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": "paulml/ECE-ILAB-Q1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use paulml/ECE-ILAB-Q1 with Docker Model Runner:
```
docker model run hf.co/paulml/ECE-ILAB-Q1
```

ECE-ILAB-Q1

This model has been produced by :

Louis Garcia, engineering student at French Engineering School ECE
Matthieu Jollard, engineering student at French Engineering School ECE
Andre-Louis Rochet, Lecturer at ECE & Co-Founder of TW3 Partners
Paul Lemaistre, CTO of TW3 Partners

With the contribution of :

ECE engineering school as sponsor

About ECE

ECE, a multi-program, multi-campus, and multi-sector engineering school specializing in digital engineering, trains engineers and technology experts for the 21st century, capable of meeting the challenges of the dual digital and sustainable development revolutions. French Engineering School ECE

merge-qwen2-72B is a merge of the following models using mergekit:

🧩 Configuration

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	40.93
IFEval (0-Shot)	78.65
BBH (3-Shot)	53.70
MATH Lvl 5 (4-Shot)	26.13
GPQA (0-shot)	18.23
MuSR (0-shot)	18.81
MMLU-PRO (5-shot)	50.06

Downloads last month: 17

Safetensors

Model size

73B params

Tensor type

BF16

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

78.650
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

53.700
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

26.130
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

18.230
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

18.810
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

50.060