Instructions to use SpaceYL/ECE_Poirot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SpaceYL/ECE_Poirot with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SpaceYL/ECE_Poirot")
model = AutoModelForCausalLM.from_pretrained("SpaceYL/ECE_Poirot")
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

vLLM

How to use SpaceYL/ECE_Poirot with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SpaceYL/ECE_Poirot

SGLang

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

Docker Model Runner
How to use SpaceYL/ECE_Poirot with Docker Model Runner:
```
docker model run hf.co/SpaceYL/ECE_Poirot
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

SpaceYL/ECE_Poirot

First model merged on the ECE intelligence Lab proprietary GPUs

This model has been produced by:

LALAIN Youri, engineering student at French Engineering School ECE
RAGE LILIAN, engineering student at French Engineering School ECE

Under the supervision of:

Andre-Louis Rochet, Lecturer at ECE, Co-founder at TW3 Partners
Paul Lemaistre, Lecturer at ECE, CTO at TW3 Partners
Mohammed Mounir, Solution Architect at Exaion
Hervé Chibois, Infrastructure Expert at Exaion
Des Bontés Sonafouo, Chef de projet IT at Omnes

With the contribution of:

ECE engineering school as sponsor and financial contributor
François STEPHAN as director of ECE
Gérard REUS as acting director of iLAB

Supervisory structure

The iLab (intelligence Lab) is a structure created by the ECE and dedicated to artificial intelligence

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.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: bond005/meno-tiny-0.1
        layer_range: [0, 28]  
      - model: Qwen/Qwen2.5-1.5B-Instruct
        layer_range: [0, 28]  
merge_method: slerp
base_model: Qwen/Qwen2.5-1.5B-Instruct
parameters:
  t:
    - filter: self_attn
      value: [0, 0.25, 0.5, 0.75, 1]
    - filter: mlp
      value: [1, 0.75, 0.5, 0.25, 0]
    - value: 0.5
dtype: bfloat16

Downloads last month: 11

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for SpaceYL/ECE_Poirot

Qwen/Qwen2.5-1.5B-Instruct

bond005/meno-tiny-0.1

Merge model

this model

Quantizations

4 models