Instructions to use Youlln/ECE-PRYMMAL1B-FT-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Youlln/ECE-PRYMMAL1B-FT-V1 with Transformers:

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

pipe = pipeline("text-generation", model="Youlln/ECE-PRYMMAL1B-FT-V1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Youlln/ECE-PRYMMAL1B-FT-V1")
model = AutoModelForCausalLM.from_pretrained("Youlln/ECE-PRYMMAL1B-FT-V1")
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 Youlln/ECE-PRYMMAL1B-FT-V1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Youlln/ECE-PRYMMAL1B-FT-V1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Youlln/ECE-PRYMMAL1B-FT-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Youlln/ECE-PRYMMAL1B-FT-V1

SGLang

How to use Youlln/ECE-PRYMMAL1B-FT-V1 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 "Youlln/ECE-PRYMMAL1B-FT-V1" \
    --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": "Youlln/ECE-PRYMMAL1B-FT-V1",
		"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 "Youlln/ECE-PRYMMAL1B-FT-V1" \
        --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": "Youlln/ECE-PRYMMAL1B-FT-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Youlln/ECE-PRYMMAL1B-FT-V1 with Docker Model Runner:
```
docker model run hf.co/Youlln/ECE-PRYMMAL1B-FT-V1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Description

The model you’re using is based on LilRg/ECE-1B-merge-PRYMMAL. Through specialized fine-tuning, this model has been trained to become highly proficient in solving complex problems. By using a dataset specifically focused on instructions (mosaicml/instruct-v3), it has gained the ability to handle advanced reasoning.

Developed by: Youri Lalain (@Youlln)
Organization: ECE engineering school

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	11.80
IFEval (0-Shot)	21.44
BBH (3-Shot)	16.19
MATH Lvl 5 (4-Shot)	6.12
GPQA (0-shot)	3.80
MuSR (0-shot)	3.87
MMLU-PRO (5-shot)	19.36

Downloads last month: 13

Safetensors

Model size

2B params

Tensor type

F32

Model tree for Youlln/ECE-PRYMMAL1B-FT-V1

Base model

LilRg/ECE-1B-merge-PRYMMAL

Finetuned

(1)

this model

Quantizations

1 model

Dataset used to train Youlln/ECE-PRYMMAL1B-FT-V1

Evaluation results

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

21.440
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

16.190
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

6.120
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

3.800
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

3.870
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

19.360